3 code implementations • 17 Dec 2021 • Wuyang Chen, Xianzhi Du, Fan Yang, Lucas Beyer, Xiaohua Zhai, Tsung-Yi Lin, Huizhong Chen, Jing Li, Xiaodan Song, Zhangyang Wang, Denny Zhou
In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.
1 code implementation • ICCV 2023 • Tianlong Chen, Xuxi Chen, Xianzhi Du, Abdullah Rashwan, Fan Yang, Huizhong Chen, Zhangyang Wang, Yeqing Li
Instead of compressing multiple tasks' knowledge into a single model, MoE separates the parameter space and only utilizes the relevant model pieces given task type and its input, which provides stabilized MTL training and ultra-efficient inference.
3 code implementations • ICCV 2023 • Xingqian Xu, Zhangyang Wang, Eric Zhang, Kai Wang, Humphrey Shi
In this work, we expand the existing single-flow diffusion pipeline into a multi-task multimodal network, dubbed Versatile Diffusion (VD), that handles multiple flows of text-to-image, image-to-text, and variations in one unified model.
1 code implementation • ICCV 2023 • Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets.
10 code implementations • NeurIPS 2021 • Yifan Jiang, Shiyu Chang, Zhangyang Wang
Our vanilla GAN architecture, dubbed TransGAN, consists of a memory-friendly transformer-based generator that progressively increases feature resolution, and correspondingly a multi-scale discriminator to capture simultaneously semantic contexts and low-level textures.
Ranked #8 on Image Generation on STL-10
1 code implementation • ICCV 2017 • Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng
This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net).
Ranked #20 on Image Dehazing on SOTS Outdoor
8 code implementations • 17 Jun 2019 • Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data?
6 code implementations • ICCV 2019 • Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.
Ranked #3 on Blind Face Restoration on CelebA-Test
1 code implementation • 6 Mar 2024 • Jiawei Zhao, Zhenyu Zhang, Beidi Chen, Zhangyang Wang, Anima Anandkumar, Yuandong Tian
Our approach reduces memory usage by up to 65. 5% in optimizer states while maintaining both efficiency and performance for pre-training on LLaMA 1B and 7B architectures with C4 dataset with up to 19. 7B tokens, and on fine-tuning RoBERTa on GLUE tasks.
2 code implementations • 10 Nov 2022 • Steven Walton, Ali Hassani, Xingqian Xu, Zhangyang Wang, Humphrey Shi
Image generation has been a long sought-after but challenging task, and performing the generation task in an efficient manner is similarly difficult.
Ranked #2 on Image Generation on FFHQ 256 x 256
1 code implementation • 21 Mar 2024 • Roberto Henschel, Levon Khachatryan, Daniil Hayrapetyan, Hayk Poghosyan, Vahram Tadevosyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions.
1 code implementation • 25 May 2023 • Xingqian Xu, Jiayi Guo, Zhangyang Wang, Gao Huang, Irfan Essa, Humphrey Shi
Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches.
5 code implementations • ICCV 2019 • Tianlong Chen, Shaojin Ding, Jingyi Xie, Ye Yuan, Wuyang Chen, Yang Yang, Zhou Ren, Zhangyang Wang
Attention mechanism has been shown to be effective for person re-identification (Re-ID).
Ranked #16 on Person Re-Identification on Market-1501-C
2 code implementations • ICLR 2020 • Wuyang Chen, Xinyu Gong, Xian-Ming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods.
Ranked #1 on Semantic Segmentation on BDD
Neural Architecture Search Real-Time Semantic Segmentation +1
4 code implementations • NeurIPS 2020 • Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang shen
In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data.
1 code implementation • 30 Mar 2023 • Vidit Goel, Elia Peruzzo, Yifan Jiang, Dejia Xu, Xingqian Xu, Nicu Sebe, Trevor Darrell, Zhangyang Wang, Humphrey Shi
We propose PAIR Diffusion, a generic framework that can enable a diffusion model to control the structure and appearance properties of each object in the image.
2 code implementations • ICCV 2019 • Xinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang Wang
Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks.
Ranked #16 on Image Generation on STL-10
1 code implementation • 28 Nov 2023 • Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Recent advancements in real-time neural rendering using point-based techniques have paved the way for the widespread adoption of 3D representations.
1 code implementation • ICCV 2019 • Shuai Yang, Zhangyang Wang, Zhaowen Wang, Ning Xu, Jiaying Liu, Zongming Guo
In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter.
1 code implementation • NeurIPS 2023 • Zhendong Wang, Yifan Jiang, Yadong Lu, Yelong Shen, Pengcheng He, Weizhu Chen, Zhangyang Wang, Mingyuan Zhou
We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models.
1 code implementation • CVPR 2019 • Wuyang Chen, Ziyu Jiang, Zhangyang Wang, Kexin Cui, Xiaoning Qian
In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy.
Ranked #4 on Land Cover Classification on DeepGlobe
1 code implementation • 27 Jul 2022 • Mukund Varma T, Peihao Wang, Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang
While prior works on NeRFs optimize a scene representation by inverting a handcrafted rendering equation, GNT achieves neural representation and rendering that generalizes across scenes using transformers at two stages.
Ranked #1 on Generalizable Novel View Synthesis on LLFF
1 code implementation • 2 Apr 2022 • Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang
Despite the rapid development of Neural Radiance Field (NeRF), the necessity of dense covers largely prohibits its wider applications.
1 code implementation • 29 Nov 2022 • Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Yi Wang, Zhangyang Wang
In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360{\deg} views that correspond well with the given reference image.
1 code implementation • 24 Jun 2023 • Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, Beidi Chen
Based on these insights, we propose Heavy Hitter Oracle (H$_2$O), a KV cache eviction policy that dynamically retains a balance of recent and H$_2$ tokens.
1 code implementation • CVPR 2022 • Zeyuan Chen, Yinbo Chen, Jingwen Liu, Xingqian Xu, Vidit Goel, Zhangyang Wang, Humphrey Shi, Xiaolong Wang
The learned implicit neural representation can be decoded to videos of arbitrary spatial resolution and frame rate.
Space-time Video Super-resolution Video Frame Interpolation +1
1 code implementation • 7 Jul 2022 • Shiwei Liu, Tianlong Chen, Xiaohan Chen, Xuxi Chen, Qiao Xiao, Boqian Wu, Tommi Kärkkäinen, Mykola Pechenizkiy, Decebal Mocanu, Zhangyang Wang
Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs).
1 code implementation • 30 May 2023 • Tianjin Huang, Lu Yin, Zhenyu Zhang, Li Shen, Meng Fang, Mykola Pechenizkiy, Zhangyang Wang, Shiwei Liu
We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures.
1 code implementation • 23 Mar 2021 • Tianlong Chen, Xiaohan Chen, Wuyang Chen, Howard Heaton, Jialin Liu, Zhangyang Wang, Wotao Yin
It automates the design of an optimization method based on its performance on a set of training problems.
1 code implementation • 22 Feb 2023 • Junjie Yang, Tianlong Chen, Mingkang Zhu, Fengxiang He, DaCheng Tao, Yingbin Liang, Zhangyang Wang
While the optimizer generalization has been recently studied, the optimizee generalization (or learning to generalize) has not been rigorously studied in the L2O context, which is the aim of this paper.
1 code implementation • 21 Dec 2023 • Hayk Manukyan, Andranik Sargsyan, Barsegh Atanyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
Recent progress in text-guided image inpainting, based on the unprecedented success of text-to-image diffusion models, has led to exceptionally realistic and visually plausible results.
4 code implementations • ICLR 2021 • Wuyang Chen, Xinyu Gong, Zhangyang Wang
Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost?
3 code implementations • 7 May 2020 • Shaojin Ding, Tianlong Chen, Xinyu Gong, Weiwei Zha, Zhangyang Wang
Speaker recognition systems based on Convolutional Neural Networks (CNNs) are often built with off-the-shelf backbones such as VGG-Net or ResNet.
Ranked #6 on Speaker Identification on VoxCeleb1 (using extra training data)
1 code implementation • 12 Jul 2015 • Zhangyang Wang, Jianchao Yang, Hailin Jin, Eli Shechtman, Aseem Agarwala, Jonathan Brandt, Thomas S. Huang
As font is one of the core design concepts, automatic font identification and similar font suggestion from an image or photo has been on the wish list of many designers.
Ranked #1 on Font Recognition on VFR-Wild
1 code implementation • CVPR 2019 • Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K. Tokuda, Roberto Hirata Junior, Roberto Cesar-Junior, Jiawan Zhang, Xiaojie Guo, Xiaochun Cao
We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images. This dataset highlights diverse data sources and image contents, and is divided into three subsets (rain streak, rain drop, rain and mist), each serving different training or evaluation purposes.
1 code implementation • 24 Jun 2018 • Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
1 code implementation • ICML 2018 • Junru Wu, Yue Wang, Zhen-Yu Wu, Zhangyang Wang, Ashok Veeraraghavan, Yingyan Lin
The current trend of pushing CNNs deeper with convolutions has created a pressing demand to achieve higher compression gains on CNNs where convolutions dominate the computation and parameter amount (e. g., GoogLeNet, ResNet and Wide ResNet).
2 code implementations • 10 Jun 2021 • Yuning You, Tianlong Chen, Yang shen, Zhangyang Wang
Unfortunately, unlike its counterpart on image data, the effectiveness of GraphCL hinges on ad-hoc data augmentations, which have to be manually picked per dataset, by either rules of thumb or trial-and-errors, owing to the diverse nature of graph data.
2 code implementations • NeurIPS 2021 • Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin, Sijia Liu, Zhangyang Wang, Yanzhi Wang
Based on our analysis, we summarize a guideline for parameter settings in regards of specific architecture characteristics, which we hope to catalyze the research progress on the topic of lottery ticket hypothesis.
2 code implementations • 26 Sep 2019 • Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang, Xiaohan Chen, Richard G. Baraniuk, Zhangyang Wang, Yingyan Lin
In this paper, we discover for the first time that the winning tickets can be identified at the very early training stage, which we term as early-bird (EB) tickets, via low-cost training schemes (e. g., early stopping and low-precision training) at large learning rates.
2 code implementations • NeurIPS 2020 • Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, Michael Carbin
For a range of downstream tasks, we indeed find matching subnetworks at 40% to 90% sparsity.
1 code implementation • ICLR 2020 • Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang, Xiaohan Chen, Richard G. Baraniuk, Zhangyang Wang, Yingyan Lin
Finally, we leverage the existence of EB tickets and the proposed mask distance to develop efficient training methods, which are achieved by first identifying EB tickets via low-cost schemes, and then continuing to train merely the EB tickets towards the target accuracy.
2 code implementations • 20 Jun 2018 • Mostafa Karimi, Di wu, Zhangyang Wang, Yang shen
Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI).
Ranked #2 on Drug Discovery on BindingDB IC50
1 code implementation • 24 Aug 2021 • Tianlong Chen, Kaixiong Zhou, Keyu Duan, Wenqing Zheng, Peihao Wang, Xia Hu, Zhangyang Wang
In view of those, we present the first fair and reproducible benchmark dedicated to assessing the "tricks" of training deep GNNs.
1 code implementation • NeurIPS 2021 • Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Anima Anandkumar, Zhangyang Wang
Diversity and hardness are two complementary dimensions of data augmentation to achieve robustness.
1 code implementation • 19 Sep 2022 • Zhiwen Fan, Peihao Wang, Yifan Jiang, Xinyu Gong, Dejia Xu, Zhangyang Wang
Our framework, called NeRF with Self-supervised Object Segmentation NeRF-SOS, couples object segmentation and neural radiance field to segment objects in any view within a scene.
1 code implementation • CVPR 2022 • Tianlong Chen, Peihao Wang, Zhiwen Fan, Zhangyang Wang
Inspired by that, we propose Augmented NeRF (Aug-NeRF), which for the first time brings the power of robust data augmentations into regularizing the NeRF training.
1 code implementation • NeurIPS 2018 • Nitin Bansal, Xiaohan Chen, Zhangyang Wang
This paper seeks to answer the question: as the (near-) orthogonality of weights is found to be a favorable property for training deep convolutional neural networks, how can we enforce it in more effective and easy-to-use ways?
1 code implementation • NeurIPS 2018 • Nitin Bansal, Xiaohan Chen, Zhangyang Wang
This paper seeks to answer the question: as the (near-) orthogonality of weights is found to be a favorable property for training deep convolutional neural networks, how can we enforce it in more effective and easy-to-use ways?
1 code implementation • 25 May 2023 • Zhiwen Fan, Panwang Pan, Peihao Wang, Yifan Jiang, Dejia Xu, Hanwen Jiang, Zhangyang Wang
To mitigate this issue, we propose a general paradigm for object pose estimation, called Promptable Object Pose Estimation (POPE).
3 code implementations • ICML 2020 • Yonggan Fu, Wuyang Chen, Haotao Wang, Haoran Li, Yingyan Lin, Zhangyang Wang
Inspired by the recent success of AutoML in deep compression, we introduce AutoML to GAN compression and develop an AutoGAN-Distiller (AGD) framework.
2 code implementations • ECCV 2020 • Haotao Wang, Shupeng Gui, Haichuan Yang, Ji Liu, Zhangyang Wang
Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications, and recently start to be deployed to resource-constrained mobile devices.
1 code implementation • NeurIPS 2020 • Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations that are consistent under both data augmentations and adversarial perturbations.
1 code implementation • 5 Apr 2022 • Zhiwen Fan, Yifan Jiang, Peihao Wang, Xinyu Gong, Dejia Xu, Zhangyang Wang
Representing visual signals by implicit representation (e. g., a coordinate based deep network) has prevailed among many vision tasks.
1 code implementation • ICML 2020 • Yuning You, Tianlong Chen, Zhangyang Wang, Yang shen
We first elaborate three mechanisms to incorporate self-supervision into GCNs, analyze the limitations of pretraining & finetuning and self-training, and proceed to focus on multi-task learning.
1 code implementation • 4 Jan 2022 • Yuning You, Tianlong Chen, Zhangyang Wang, Yang shen
Accordingly, we have extended the prefabricated discrete prior in the augmentation set, to a learnable continuous prior in the parameter space of graph generators, assuming that graph priors per se, similar to the concept of image manifolds, can be learned by data generation.
1 code implementation • ICCV 2021 • Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang
Image harmonization aims to improve the quality of image compositing by matching the "appearance" (\eg, color tone, brightness and contrast) between foreground and background images.
2 code implementations • 14 Jun 2017 • Ding Liu, Bihan Wen, Xianming Liu, Zhangyang Wang, Thomas S. Huang
Conventionally, image denoising and high-level vision tasks are handled separately in computer vision.
1 code implementation • 6 Sep 2018 • Ding Liu, Bihan Wen, Jianbo Jiao, Xian-Ming Liu, Zhangyang Wang, Thomas S. Huang
Second we propose a deep neural network solution that cascades two modules for image denoising and various high-level tasks, respectively, and use the joint loss for updating only the denoising network via back-propagation.
1 code implementation • 30 Mar 2023 • Eric Zhang, Kai Wang, Xingqian Xu, Zhangyang Wang, Humphrey Shi
The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry.
1 code implementation • 4 Oct 2023 • Yifan Jiang, Hao Tang, Jen-Hao Rick Chang, Liangchen Song, Zhangyang Wang, Liangliang Cao
Although the fidelity and generalizability are greatly improved, training such a powerful diffusion model requires a vast volume of training data and model parameters, resulting in a notoriously long time and high computational costs.
2 code implementations • ICCV 2019 • Zhen-Yu Wu, Karthik Suresh, Priya Narayanan, Hongyu Xu, Heesung Kwon, Zhangyang Wang
Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful.
1 code implementation • NeurIPS 2021 • Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang
For example, our sparsified DeiT-Small at (5%, 50%) sparsity for (data, architecture), improves 0. 28% top-1 accuracy, and meanwhile enjoys 49. 32% FLOPs and 4. 40% running time savings.
Ranked #20 on Efficient ViTs on ImageNet-1K (with DeiT-T)
1 code implementation • CVPR 2020 • Tianlong Chen, Sijia Liu, Shiyu Chang, Yu Cheng, Lisa Amini, Zhangyang Wang
We conduct extensive experiments to demonstrate that the proposed framework achieves large performance margins (eg, 3. 83% on robust accuracy and 1. 3% on standard accuracy, on the CIFAR-10 dataset), compared with the conventional end-to-end adversarial training baseline.
1 code implementation • NeurIPS 2021 • Tianlong Chen, Yu Cheng, Zhe Gan, Jingjing Liu, Zhangyang Wang
Training generative adversarial networks (GANs) with limited real image data generally results in deteriorated performance and collapsed models.
1 code implementation • ICLR 2021 • Haoyu Ma, Tianlong Chen, Ting-Kuei Hu, Chenyu You, Xiaohui Xie, Zhangyang Wang
Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models.
1 code implementation • ECCV 2020 • Shuai Yang, Zhangyang Wang, Jiaying Liu, Zongming Guo
We present a sketch refinement strategy, as inspired by the coarse-to-fine drawing process of the artists, which we show can help our model well adapt to casual and varied sketches without the need for real sketch training data.
1 code implementation • ICLR 2022 • Wuyang Chen, Wei Huang, Xianzhi Du, Xiaodan Song, Zhangyang Wang, Denny Zhou
The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart.
1 code implementation • 9 Mar 2022 • Peihao Wang, Wenqing Zheng, Tianlong Chen, Zhangyang Wang
The first technique, termed AttnScale, decomposes a self-attention block into low-pass and high-pass components, then rescales and combines these two filters to produce an all-pass self-attention matrix.
1 code implementation • 26 Oct 2022 • Hanxue Liang, Zhiwen Fan, Rishov Sarkar, Ziyu Jiang, Tianlong Chen, Kai Zou, Yu Cheng, Cong Hao, Zhangyang Wang
However, when deploying MTL onto those real-world systems that are often resource-constrained or latency-sensitive, two prominent challenges arise: (i) during training, simultaneously optimizing all tasks is often difficult due to gradient conflicts across tasks; (ii) at inference, current MTL regimes have to activate nearly the entire model even to just execute a single task.
1 code implementation • ICLR 2022 • Shiwei Liu, Tianlong Chen, Xiaohan Chen, Li Shen, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy
In this paper, we focus on sparse training and highlight a perhaps counter-intuitive finding, that random pruning at initialization can be quite powerful for the sparse training of modern neural networks.
1 code implementation • CVPR 2021 • Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang
We extend the scope of LTH and question whether matching subnetworks still exist in pre-trained computer vision models, that enjoy the same downstream transfer performance.
1 code implementation • 30 May 2019 • Pritish Uplavikar, Zhen-Yu Wu, Zhangyang Wang
We train our model on a dataset consisting images of 10 Jerlov water types.
1 code implementation • NeurIPS 2020 • Haoran You, Xiaohan Chen, Yongan Zhang, Chaojian Li, Sicheng Li, Zihao Liu, Zhangyang Wang, Yingyan Lin
Multiplication (e. g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs).
1 code implementation • 30 May 2023 • Rishov Sarkar, Hanxue Liang, Zhiwen Fan, Zhangyang Wang, Cong Hao
Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention in ViT and the need to activate an entire large MTL model for one task.
1 code implementation • 14 May 2019 • Ernest K. Ryu, Jialin Liu, Sicheng Wang, Xiaohan Chen, Zhangyang Wang, Wotao Yin
Plug-and-play (PnP) is a non-convex framework that integrates modern denoising priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal algorithms.
1 code implementation • 6 Jun 2021 • Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang
Hence, the key innovation in SDCLR is to create a dynamic self-competitor model to contrast with the target model, which is a pruned version of the latter.
1 code implementation • ICML 2020 • Xuxi Chen, Wuyang Chen, Tianlong Chen, Ye Yuan, Chen Gong, Kewei Chen, Zhangyang Wang
Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i. e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples.
2 code implementations • 15 Sep 2022 • Yi Wang, Zhiwen Fan, Tianlong Chen, Hehe Fan, Zhangyang Wang
Vision Transformers (ViTs) have proven to be effective, in solving 2D image understanding tasks by training over large-scale image datasets; and meanwhile as a somehow separate track, in modeling the 3D visual world too such as voxels or point clouds.
1 code implementation • 27 Apr 2022 • Qiucheng Wu, Yifan Jiang, Junru Wu, Kai Wang, Gong Zhang, Humphrey Shi, Zhangyang Wang, Shiyu Chang
To study the motion features in the latent space of StyleGAN, in this paper, we hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as "micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper "anchors" in the form of either short text or video clips.
2 code implementations • 12 Feb 2021 • Tianlong Chen, Yongduo Sui, Xuxi Chen, Aston Zhang, Zhangyang Wang
With graphs rapidly growing in size and deeper graph neural networks (GNNs) emerging, the training and inference of GNNs become increasingly expensive.
1 code implementation • CVPR 2022 • Zhiwen Fan, Tianlong Chen, Peihao Wang, Zhangyang Wang
CADTransformer tokenizes directly from the set of graphical primitives in CAD drawings, and correspondingly optimizes line-grained semantic and instance symbol spotting altogether by a pair of prediction heads.
2 code implementations • 14 Oct 2022 • Keyu Duan, Zirui Liu, Peihao Wang, Wenqing Zheng, Kaixiong Zhou, Tianlong Chen, Xia Hu, Zhangyang Wang
Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs).
Ranked #2 on Node Property Prediction on ogbn-products
3 code implementations • NeurIPS 2018 • Xiaohan Chen, Jialin Liu, Zhangyang Wang, Wotao Yin
In this work, we study unfolded ISTA (Iterative Shrinkage Thresholding Algorithm) for sparse signal recovery.
1 code implementation • Submitted to ICLR 2022 • Wentao Zhu, Yufang Huang, Xiufeng Xie, Wenxian Liu, Jincan Deng, Debing Zhang, Zhangyang Wang, Ji Liu
For video content creation and understanding, the shot boundary detection (SBD) is one of the most essential components in various scenarios.
Ranked #1 on Camera shot boundary detection on ClipShots
1 code implementation • 16 Apr 2021 • Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang
However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle for the efficient implementation of BNN training.
Ranked #167 on Image Classification on CIFAR-10
1 code implementation • 23 Mar 2021 • Xingqian Xu, Zhangyang Wang, Humphrey Shi
In this work, we propose UltraSR, a simple yet effective new network design based on implicit image functions in which we deeply integrated spatial coordinates and periodic encoding with the implicit neural representation.
2 code implementations • ICLR 2022 • Wenqing Zheng, Edward W Huang, Nikhil Rao, Sumeet Katariya, Zhangyang Wang, Karthik Subbian
We propose Cold Brew, a teacher-student distillation approach to address the SCS and noisy-neighbor challenges for GNNs.
1 code implementation • 27 Feb 2023 • Wenqing Zheng, Edward W Huang, Nikhil Rao, Zhangyang Wang, Karthik Subbian
We identify this setting as Graph Intersection-induced Transfer Learning (GITL), which is motivated by practical applications in e-commerce or academic co-authorship predictions.
2 code implementations • 29 Aug 2018 • Xiaofeng Zhang, Zhangyang Wang, Dong Liu, Qing Ling
Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else.
1 code implementation • 22 Feb 2021 • Xinyu Gong, Wuyang Chen, Tianlong Chen, Zhangyang Wang
We present Sandwich Batch Normalization (SaBN), a frustratingly easy improvement of Batch Normalization (BN) with only a few lines of code changes.
Ranked #20 on Neural Architecture Search on NAS-Bench-201, CIFAR-100
2 code implementations • NeurIPS 2019 • Shupeng Gui, Haotao Wang, Chen Yu, Haichuan Yang, Zhangyang Wang, Ji Liu
Deep model compression has been extensively studied, and state-of-the-art methods can now achieve high compression ratios with minimal accuracy loss.
1 code implementation • NeurIPS 2023 • Zhendong Wang, Yifan Jiang, Huangjie Zheng, Peihao Wang, Pengcheng He, Zhangyang Wang, Weizhu Chen, Mingyuan Zhou
Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e. g.$, as few as 5, 000 images to train from scratch.
1 code implementation • 30 Jun 2018 • Yu Liu, Guanlong Zhao, Boyuan Gong, Yang Li, Ritu Raj, Niraj Goel, Satya Kesav, Sandeep Gottimukkala, Zhangyang Wang, Wenqi Ren, DaCheng Tao
Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e. g., object detection) of hazy images.
1 code implementation • 17 Dec 2019 • Ye Yuan, Wuyang Chen, Yang Yang, Zhangyang Wang
This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels.
1 code implementation • ICLR 2022 • Shixing Yu, Tianlong Chen, Jiayi Shen, Huan Yuan, Jianchao Tan, Sen yang, Ji Liu, Zhangyang Wang
Vision transformers (ViTs) have gained popularity recently.
1 code implementation • NeurIPS 2020 • Haotao Wang, Tianlong Chen, Shupeng Gui, Ting-Kuei Hu, Ji Liu, Zhangyang Wang
The trained model could be adjusted among different standard and robust accuracies "for free" at testing time.
1 code implementation • 7 Oct 2022 • Tianxin Wei, Yuning You, Tianlong Chen, Yang shen, Jingrui He, Zhangyang Wang
This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL).
1 code implementation • ICCV 2023 • Wenyan Cong, Hanxue Liang, Peihao Wang, Zhiwen Fan, Tianlong Chen, Mukund Varma, Yi Wang, Zhangyang Wang
Cross-scene generalizable NeRF models, which can directly synthesize novel views of unseen scenes, have become a new spotlight of the NeRF field.
5 code implementations • 12 Jun 2019 • Zhen-Yu Wu, Haotao Wang, Zhaowen Wang, Hailin Jin, Zhangyang Wang
We first discuss an innovative heuristic of cross-dataset training and evaluation, enabling the use of multiple single-task datasets (one with target task labels and the other with privacy labels) in our problem.
1 code implementation • 2 Mar 2023 • Tianlong Chen, Zhenyu Zhang, Ajay Jaiswal, Shiwei Liu, Zhangyang Wang
Despite their remarkable achievement, gigantic transformers encounter significant drawbacks, including exorbitant computational and memory footprints during training, as well as severe collapse evidenced by a high degree of parameter redundancy.
1 code implementation • 22 May 2020 • Prateek Shroff, Tianlong Chen, Yunchao Wei, Zhangyang Wang
In this paper, we tried to focus on these marginal differences to extract more representative features.
1 code implementation • 8 Oct 2023 • Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Mykola Pechenizkiy, Yi Liang, Zhangyang Wang, Shiwei Liu
Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge when it comes to practical deployment due to their colossal model size.
3 code implementations • ECCV 2018 • Zhen-Yu Wu, Zhangyang Wang, Zhaowen Wang, Hailin Jin
This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework.
1 code implementation • ICLR 2022 • Tianlong Chen, Zhenyu Zhang, Pengjun Wang, Santosh Balachandra, Haoyu Ma, Zehao Wang, Zhangyang Wang
We introduce two alternatives for sparse adversarial training: (i) static sparsity, by leveraging recent results from the lottery ticket hypothesis to identify critical sparse subnetworks arising from the early training; (ii) dynamic sparsity, by allowing the sparse subnetwork to adaptively adjust its connectivity pattern (while sticking to the same sparsity ratio) throughout training.
1 code implementation • ICLR 2022 • Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness.
1 code implementation • 4 Jul 2022 • Haotao Wang, Aston Zhang, Yi Zhu, Shuai Zheng, Mu Li, Alex Smola, Zhangyang Wang
However, in real-world applications, it is common for the training sets to have long-tailed distributions.
1 code implementation • 28 Apr 2023 • Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, Kevin Wang, Yihan Xi, Dejia Xu, Zhangyang Wang
For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy.
2 code implementations • 22 May 2019 • Sicheng Wang, Bihan Wen, Junru Wu, DaCheng Tao, Zhangyang Wang
Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level computer vision tasks as the pre-processing step.
1 code implementation • 13 May 2021 • Aaditya Singh, Shreeshail Hingane, Xinyu Gong, Zhangyang Wang
We demonstrate that plugging SAFIN into the base network of another state-of-the-art method results in enhanced stylization.
1 code implementation • ICML 2020 • Wuyang Chen, Zhiding Yu, Zhangyang Wang, Anima Anandkumar
Models trained on synthetic images often face degraded generalization to real data.
1 code implementation • 8 Jul 2022 • Peihao Wang, Zhiwen Fan, Tianlong Chen, Zhangyang Wang
In this paper, we present a generic INR framework that achieves both data and training efficiency by learning a Neural Implicit Dictionary (NID) from a data collection and representing INR as a functional combination of basis sampled from the dictionary.
1 code implementation • 14 Jul 2022 • Peihao Wang, Shenghao Yang, Yunyu Liu, Zhangyang Wang, Pan Li
Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data and further solve relevant prediction tasks built upon such higher-order relations.
2 code implementations • 13 Feb 2024 • Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, Zhangyang Wang
Graph Neural Networks (GNNs) have empowered the advance in graph-structured data analysis.
2 code implementations • ICLR 2021 • Wuyang Chen, Zhiding Yu, Shalini De Mello, Sifei Liu, Jose M. Alvarez, Zhangyang Wang, Anima Anandkumar
Training on synthetic data can be beneficial for label or data-scarce scenarios.
2 code implementations • CVPR 2020 • Yuning You, Tianlong Chen, Zhangyang Wang, Yang shen
Graph convolution networks (GCN) are increasingly popular in many applications, yet remain notoriously hard to train over large graph datasets.
1 code implementation • 21 Sep 2021 • Abduallah Mohamed, Huancheng Chen, Zhangyang Wang, Christian Claudel
We propose Skeleton-Graph, a deep spatio-temporal graph CNN model that predicts the future 3D skeleton poses in a single pass from the 2D ones.
Ranked #1 on Trajectory Prediction on PROX
1 code implementation • 9 Feb 2022 • Tianlong Chen, Xuxi Chen, Xiaolong Ma, Yanzhi Wang, Zhangyang Wang
The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i. e., winning tickets) that can be trained in isolation to match full accuracy.
2 code implementations • NeurIPS 2021 • Shiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin, Huanyu Kou, Li Shen, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization).
Ranked #3 on Sparse Learning on ImageNet
1 code implementation • ICLR 2022 • Lu Miao, Xiaolong Luo, Tianlong Chen, Wuyang Chen, Dong Liu, Zhangyang Wang
Conventional methods often require (iterative) pruning followed by re-training, which not only incurs large overhead beyond the original DNN training but also can be sensitive to retraining hyperparameters.
1 code implementation • NeurIPS 2021 • Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan
We propose a paradigm shift from fitting the whole architecture space using one strong predictor, to progressively fitting a search path towards the high-performance sub-space through a set of weaker predictors.
1 code implementation • NeurIPS 2021 • Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes.
1 code implementation • NeurIPS 2021 • Ziyu Jiang, Tianlong Chen, Ting Chen, Zhangyang Wang
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes.
1 code implementation • 20 Jul 2022 • Zhiyuan Mao, Ajay Jaiswal, Zhangyang Wang, Stanley H. Chan
Image restoration algorithms for atmospheric turbulence are known to be much more challenging to design than traditional ones such as blur or noise because the distortion caused by the turbulence is an entanglement of spatially varying blur, geometric distortion, and sensor noise.
1 code implementation • ICCV 2023 • Yihua Zhang, Ruisi Cai, Tianlong Chen, Guanhua Zhang, huan zhang, Pin-Yu Chen, Shiyu Chang, Zhangyang Wang, Sijia Liu
Since the lack of robustness has become one of the main hurdles for CNNs, in this paper we ask: How to adversarially robustify a CNN-based MoE model?
1 code implementation • 3 Dec 2023 • Junjie Yang, Jinze Zhao, Peihao Wang, Zhangyang Wang, Yingbin Liang
However, vanilla ControlNet generally requires extensive training of around 5000 steps to achieve a desirable control for a single task.
1 code implementation • NeurIPS 2020 • Tianlong Chen, Weiyi Zhang, Jingyang Zhou, Shiyu Chang, Sijia Liu, Lisa Amini, Zhangyang Wang
Learning to optimize (L2O) has gained increasing attention since classical optimizers require laborious problem-specific design and hyperparameter tuning.
2 code implementations • ICLR 2022 • Shiwei Liu, Tianlong Chen, Zahra Atashgahi, Xiaohan Chen, Ghada Sokar, Elena Mocanu, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu
Our framework, FreeTickets, is defined as the ensemble of these relatively cheap sparse subnetworks.
1 code implementation • the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining 2021 • Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang, Hiroko Dodge, Jiayu Zhou
While adversarial learning is commonly used in centralized learning for mitigating bias, there are significant barriers when extending it to the federated framework.
1 code implementation • 18 Feb 2024 • Yihua Zhang, Pingzhi Li, Junyuan Hong, Jiaxiang Li, Yimeng Zhang, Wenqing Zheng, Pin-Yu Chen, Jason D. Lee, Wotao Yin, Mingyi Hong, Zhangyang Wang, Sijia Liu, Tianlong Chen
In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard.
1 code implementation • 6 Jun 2021 • Zhenyu Zhang, Xuxi Chen, Tianlong Chen, Zhangyang Wang
We observe that a high-quality winning ticket can be found with training and pruning the dense network on the very compact PrAC set, which can substantially save training iterations for the ticket finding process.
1 code implementation • 18 Jun 2021 • Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
In this paper, we study a novel FL strategy: propagating adversarial robustness from rich-resource users that can afford AT, to those with poor resources that cannot afford it, during federated learning.
1 code implementation • 26 Aug 2021 • Wuyang Chen, Xinyu Gong, Junru Wu, Yunchao Wei, Humphrey Shi, Zhicheng Yan, Yi Yang, Zhangyang Wang
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation.
1 code implementation • 18 Dec 2021 • Sameer Bibikar, Haris Vikalo, Zhangyang Wang, Xiaohan Chen
Federated learning (FL) enables distribution of machine learning workloads from the cloud to resource-limited edge devices.
1 code implementation • 3 Mar 2023 • Shiwei Liu, Tianlong Chen, Zhenyu Zhang, Xuxi Chen, Tianjin Huang, Ajay Jaiswal, Zhangyang Wang
In pursuit of a more general evaluation and unveiling the true potential of sparse algorithms, we introduce "Sparsity May Cry" Benchmark (SMC-Bench), a collection of carefully-curated 4 diverse tasks with 10 datasets, that accounts for capturing a wide range of domain-specific and sophisticated knowledge.
1 code implementation • 2 Oct 2020 • Zhenyu Wu, Duc Hoang, Shih-Yao Lin, Yusheng Xie, Liangjian Chen, Yen-Yu Lin, Zhangyang Wang, Wei Fan
Estimating the 3D hand pose from a monocular RGB image is important but challenging.
1 code implementation • CVPR 2022 • Tianlong Chen, Zhenyu Zhang, Yu Cheng, Ahmed Awadallah, Zhangyang Wang
However, a "head-to-toe assessment" regarding the extent of redundancy in ViTs, and how much we could gain by thoroughly mitigating such, has been absent for this field.
1 code implementation • CVPR 2022 • Tianlong Chen, Zhenyu Zhang, Yihua Zhang, Shiyu Chang, Sijia Liu, Zhangyang Wang
Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger.
2 code implementations • ICLR 2020 • Ting-Kuei Hu, Tianlong Chen, Haotao Wang, Zhangyang Wang
Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) (Tsipras et al., 2019).
1 code implementation • 26 Jun 2022 • Ajay Jaiswal, Haoyu Ma, Tianlong Chen, Ying Ding, Zhangyang Wang
Pruning large neural networks to create high-quality, independently trainable sparse masks, which can maintain similar performance to their dense counterparts, is very desirable due to the reduced space and time complexity.
1 code implementation • 27 Feb 2023 • Ziyu Jiang, Yinpeng Chen, Mengchen Liu, Dongdong Chen, Xiyang Dai, Lu Yuan, Zicheng Liu, Zhangyang Wang
This motivates us to shift the paradigm from combining loss at the end, to choosing the proper learning method per network layer.
1 code implementation • ICCV 2023 • Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, Zhangyang Wang
In this paper, we enhance ViG by transcending conventional "pairwise" linkages and harnessing the power of the hypergraph to encapsulate image information.
1 code implementation • 29 Aug 2022 • Gregory Holste, Song Wang, Ziyu Jiang, Thomas C. Shen, George Shih, Ronald M. Summers, Yifan Peng, Zhangyang Wang
Imaging exams, such as chest radiography, will yield a small set of common findings and a much larger set of uncommon findings.
Ranked #1 on Long-tail Learning on MIMIC-CXR-LT
1 code implementation • 12 Dec 2017 • Boyi Li, Wenqi Ren, Dengpan Fu, DaCheng Tao, Dan Feng, Wen-Jun Zeng, Zhangyang Wang
We present a comprehensive study and evaluation of existing single image dehazing algorithms, using a new large-scale benchmark consisting of both synthetic and real-world hazy images, called REalistic Single Image DEhazing (RESIDE).
1 code implementation • 22 Mar 2021 • Tianlong Chen, Yu Cheng, Zhe Gan, JianFeng Wang, Lijuan Wang, Zhangyang Wang, Jingjing Liu
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models.
1 code implementation • NeurIPS 2021 • Xiaohan Chen, Jialin Liu, Zhangyang Wang, Wotao Yin
Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) introduces the concept of unrolling an iterative algorithm and training it like a neural network.
1 code implementation • 27 Nov 2023 • Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang
To ensure that the prompts do not leak private information, we introduce the first private prompt generation mechanism, by a differentially-private (DP) ensemble of in-context learning with private demonstrations.
1 code implementation • ICLR 2020 • Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma
On the other hand, the trained classifiers have traditionally been evaluated on small and fixed sets of test images, which are deemed to be extremely sparsely distributed in the space of all natural images.
1 code implementation • 10 Jul 2022 • Yan Han, Gregory Holste, Ying Ding, Ahmed Tewfik, Yifan Peng, Zhangyang Wang
Using the learned self-attention of its image branch, RGT extracts a bounding box for which to compute radiomic features, which are further processed by the radiomics branch; learned image and radiomic features are then fused and mutually interact via cross-attention layers.
1 code implementation • 14 Feb 2024 • Harry Dong, Xinyu Yang, Zhenyu Zhang, Zhangyang Wang, Yuejie Chi, Beidi Chen
Many computational factors limit broader deployment of large language models.
1 code implementation • 4 Jul 2022 • Haotao Wang, Aston Zhang, Shuai Zheng, Xingjian Shi, Mu Li, Zhangyang Wang
In addition, NoFrost achieves a $23. 56\%$ adversarial robustness against PGD attack, which improves the $13. 57\%$ robustness in BN-based AT.
1 code implementation • 25 Jun 2020 • Yi Wang, Jingyang Zhou, Tianlong Chen, Sijia Liu, Shiyu Chang, Chandrajit Bajaj, Zhangyang Wang
Contrary to the traditional adversarial patch, this new form of attack is mapped into the 3D object world and back-propagates to the 2D image domain through differentiable rendering.
1 code implementation • ICLR 2023 • Shuyang Yu, Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
We propose to take advantage of such heterogeneity and turn the curse into a blessing that facilitates OoD detection in FL.
1 code implementation • NeurIPS 2019 • Yue Cao, Tianlong Chen, Zhangyang Wang, Yang shen
Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks.
1 code implementation • ACL 2021 • Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Zhangyang Wang, Jingjing Liu
Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks.
1 code implementation • 4 Apr 2022 • Diganta Misra, Bharat Runwal, Tianlong Chen, Zhangyang Wang, Irina Rish
With the latest advances in deep learning, there has been a lot of focus on the online learning paradigm due to its relevance in practical settings.
1 code implementation • ICCV 2023 • Ajay Jaiswal, Xingguang Zhang, Stanley H. Chan, Zhangyang Wang
Although fast and physics-grounded simulation tools have been introduced to help the deep-learning models adapt to real-world turbulence conditions recently, the training of such models only relies on the synthetic data and ground truth pairs.
1 code implementation • 3 Jan 2020 • Jianghao Shen, Yonggan Fu, Yue Wang, Pengfei Xu, Zhangyang Wang, Yingyan Lin
The core idea of DFS is to hypothesize layer-wise quantization (to different bitwidths) as intermediate "soft" choices to be made between fully utilizing and skipping a layer.
1 code implementation • 15 Jun 2022 • Tianlong Chen, huan zhang, Zhenyu Zhang, Shiyu Chang, Sijia Liu, Pin-Yu Chen, Zhangyang Wang
Certifiable robustness is a highly desirable property for adopting deep neural networks (DNNs) in safety-critical scenarios, but often demands tedious computations to establish.
1 code implementation • 1 Aug 2021 • Zeyuan Chen, Yifan Jiang, Dong Liu, Zhangyang Wang
We present \underline{C}oordinated \underline{E}nhancement for \underline{R}eal-world \underline{L}ow-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework.
1 code implementation • 9 Apr 2022 • Xin Hu, Zhenyu Wu, Hao-Yu Miao, Siqi Fan, Taiyu Long, Zhenyu Hu, Pengcheng Pi, Yi Wu, Zhou Ren, Zhangyang Wang, Gang Hua
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.
1 code implementation • 13 Jun 2023 • Panwang Pan, Zhiwen Fan, Brandon Y. Feng, Peihao Wang, Chenxin Li, Zhangyang Wang
The accurate estimation of six degrees-of-freedom (6DoF) object poses is essential for many applications in robotics and augmented reality.
1 code implementation • 5 Jul 2023 • Guihong Li, Duc Hoang, Kartikeya Bhardwaj, Ming Lin, Zhangyang Wang, Radu Marculescu
Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process.
1 code implementation • CVPR 2022 • Xinglong Sun, Ali Hassani, Zhangyang Wang, Gao Huang, Humphrey Shi
We analyzed the pruning masks generated with DiSparse and observed strikingly similar sparse network architecture identified by each task even before the training starts.
1 code implementation • 19 Nov 2022 • Zhenglun Kong, Haoyu Ma, Geng Yuan, Mengshu Sun, Yanyue Xie, Peiyan Dong, Xin Meng, Xuan Shen, Hao Tang, Minghai Qin, Tianlong Chen, Xiaolong Ma, Xiaohui Xie, Zhangyang Wang, Yanzhi Wang
Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization.
1 code implementation • 30 Dec 2022 • Wenqing Zheng, S P Sharan, Zhiwen Fan, Kevin Wang, Yihan Xi, Zhangyang Wang
Learning efficient and interpretable policies has been a challenging task in reinforcement learning (RL), particularly in the visual RL setting with complex scenes.
1 code implementation • 24 Feb 2023 • Ruisi Cai, Zhenyu Zhang, Zhangyang Wang
Given a robust model trained to be resilient to one or multiple types of distribution shifts (e. g., natural image corruptions), how is that "robustness" encoded in the model weights, and how easily can it be disentangled and/or "zero-shot" transferred to some other models?
1 code implementation • 5 Mar 2024 • Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang
To address this problem, this paper introduces Multi-scale Positional Encoding (Ms-PoE) which is a simple yet effective plug-and-play approach to enhance the capacity of LLMs to handle the relevant information located in the middle of the context, without fine-tuning or introducing any additional overhead.
1 code implementation • 27 Feb 2021 • Jiebin Yan, Yu Zhong, Yuming Fang, Zhangyang Wang, Kede Ma
A natural question then arises: Does the superior performance on the closed (and frequently re-used) test sets transfer to the open visual world with unconstrained variations?
1 code implementation • 12 Oct 2022 • Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang
As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples.
1 code implementation • 26 Nov 2019 • Ye Yuan, Wuyang Chen, Tianlong Chen, Yang Yang, Zhou Ren, Zhangyang Wang, Gang Hua
Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification.
1 code implementation • NeurIPS 2020 • Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan Lin
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due to the limited resources available at the edge and the required massive training costs for state-of-the-art (SOTA) DNNs.
1 code implementation • 24 Oct 2022 • S P Sharan, Wenqing Zheng, Kuo-Feng Hsu, Jiarong Xing, Ang Chen, Zhangyang Wang
At the core of our proposal is a novel symbolic branching algorithm that enables the rule to be aware of the context in terms of various network conditions, eventually converting the NN policy into a symbolic tree.
1 code implementation • 18 Jun 2023 • Ajay Jaiswal, Shiwei Liu, Tianlong Chen, Ying Ding, Zhangyang Wang
By dividing giant graph data, we build multiple independently and parallelly trained weaker GNNs (soup ingredient) without any intermediate communication, and combine their strength using a greedy interpolation soup procedure to achieve state-of-the-art performance.
1 code implementation • 29 Sep 2023 • Lu Yin, Ajay Jaiswal, Shiwei Liu, Souvik Kundu, Zhangyang Wang
Contrary to this belief, this paper presents a counter-argument: small-magnitude weights of pre-trained model weights encode vital knowledge essential for tackling difficult downstream tasks - manifested as the monotonic relationship between the performance drop of downstream tasks across the difficulty spectrum, as we prune more pre-trained weights by magnitude.
1 code implementation • NeurIPS 2021 • Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Jingjing Liu, Zhangyang Wang
Based on these results, we articulate the Elastic Lottery Ticket Hypothesis (E-LTH): by mindfully replicating (or dropping) and re-ordering layers for one network, its corresponding winning ticket could be stretched (or squeezed) into a subnetwork for another deeper (or shallower) network from the same family, whose performance is nearly the same competitive as the latter's winning ticket directly found by IMP.
1 code implementation • ICLR 2022 • Wenqing Zheng, Tianlong Chen, Ting-Kuei Hu, Zhangyang Wang
Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks.
1 code implementation • 23 Nov 2022 • Yan Han, Edward W Huang, Wenqing Zheng, Nikhil Rao, Zhangyang Wang, Karthik Subbian
With these hyperedges, we augment the original bipartite graph into a new \textit{hypergraph}.
1 code implementation • 28 Nov 2022 • Tianjin Huang, Tianlong Chen, Meng Fang, Vlado Menkovski, Jiaxu Zhao, Lu Yin, Yulong Pei, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy, Shiwei Liu
Recent works have impressively demonstrated that there exists a subnetwork in randomly initialized convolutional neural networks (CNNs) that can match the performance of the fully trained dense networks at initialization, without any optimization of the weights of the network (i. e., untrained networks).
1 code implementation • 18 Jun 2023 • Ajay Jaiswal, Shiwei Liu, Tianlong Chen, Ying Ding, Zhangyang Wang
Motivated by the recent observations of model soups, which suggest that fine-tuned weights of multiple models can be merged to a better minima, we propose Instant Soup Pruning (ISP) to generate lottery ticket quality subnetworks, using a fraction of the original IMP cost by replacing the expensive intermediate pruning stages of IMP with computationally efficient weak mask generation and aggregation routine.
1 code implementation • ICLR 2018 • Mengying Sun, Inci M. Baytas, Liang Zhan, Zhangyang Wang, Jiayu Zhou
Over the past decade a wide spectrum of machine learning models have been developed to model the neurodegenerative diseases, associating biomarkers, especially non-intrusive neuroimaging markers, with key clinical scores measuring the cognitive status of patients.
2 code implementations • 20 Jul 2017 • Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng
This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net).
1 code implementation • 1 Jun 2019 • Ziyu Jiang, Kate Von Ness, Julie Loisel, Zhangyang Wang
Arctic environments are rapidly changing under the warming climate.
1 code implementation • ECCV 2020 • Chaojian Li, Tianlong Chen, Haoran You, Zhangyang Wang, Yingyan Lin
There has been an explosive demand for bringing machine learning (ML) powered intelligence into numerous Internet-of-Things (IoT) devices.
1 code implementation • 10 Jun 2021 • Mingkang Zhu, Tianlong Chen, Zhangyang Wang
Compared to state-of-the-art methods, our homotopy attack leads to significantly fewer perturbations, e. g., reducing 42. 91% on CIFAR-10 and 75. 03% on ImageNet (average case, targeted attack), at similar maximal perturbation magnitudes, when still achieving 100% attack success rates.
1 code implementation • 24 Jun 2021 • Ting-Kuei Hu, Fernando Gama, Tianlong Chen, Wenqing Zheng, Zhangyang Wang, Alejandro Ribeiro, Brian M. Sadler
Our framework is implemented by a cascade of a convolutional and a graph neural network (CNN / GNN), addressing agent-level visual perception and feature learning, as well as swarm-level communication, local information aggregation and agent action inference, respectively.
1 code implementation • 30 Oct 2021 • Xuxi Chen, Tianlong Chen, Weizhu Chen, Ahmed Hassan Awadallah, Zhangyang Wang, Yu Cheng
To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights.
1 code implementation • 9 Jun 2022 • Tianlong Chen, Zhenyu Zhang, Sijia Liu, Yang Zhang, Shiyu Chang, Zhangyang Wang
For example, on downstream CIFAR-10/100 datasets, we identify double-win matching subnetworks with the standard, fast adversarial, and adversarial pre-training from ImageNet, at 89. 26%/73. 79%, 89. 26%/79. 03%, and 91. 41%/83. 22% sparsity, respectively.
1 code implementation • NeurIPS 2020 • Xiaohan Chen, Zhangyang Wang, Siyu Tang, Krikamol Muandet
Meta-learning improves generalization of machine learning models when faced with previously unseen tasks by leveraging experiences from different, yet related prior tasks.
1 code implementation • NeurIPS 2021 • Xuxi Chen, Tianlong Chen, Zhenyu Zhang, Zhangyang Wang
The lottery ticket hypothesis (LTH) emerges as a promising framework to leverage a special sparse subnetwork (i. e., winning ticket) instead of a full model for both training and inference, that can lower both costs without sacrificing the performance.
1 code implementation • 14 Oct 2022 • Ajay Jaiswal, Peihao Wang, Tianlong Chen, Justin F. Rousseau, Ying Ding, Zhangyang Wang
In this paper, firstly, we provide a new perspective of gradient flow to understand the substandard performance of deep GCNs and hypothesize that by facilitating healthy gradient flow, we can significantly improve their trainability, as well as achieve state-of-the-art (SOTA) level performance from vanilla-GCNs.
1 code implementation • 29 May 2023 • Jialin Liu, Xiaohan Chen, Zhangyang Wang, Wotao Yin, HanQin Cai
Learning to Optimize (L2O), a technique that utilizes machine learning to learn an optimization algorithm automatically from data, has gained arising attention in recent years.
1 code implementation • 2 Oct 2023 • Ajay Jaiswal, Zhe Gan, Xianzhi Du, BoWen Zhang, Zhangyang Wang, Yinfei Yang
Recently, several works have shown significant success in training-free and data-free compression (pruning and quantization) of LLMs that achieve 50 - 60% sparsity and reduce the bit width to 3 or 4 bits per weight, with negligible degradation of perplexity over the uncompressed baseline.
1 code implementation • 28 Feb 2018 • Dong Liu, Ke Sun, Zhangyang Wang, Runsheng Liu, Zheng-Jun Zha
We propose an interpretable deep structure namely Frank-Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving an $L_p$-norm constrained problem with $p\geq 1$.
1 code implementation • NIPS 2022 • Mukund Varma T, Xuxi Chen, Zhenyu Zhang, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang
Improving the performance of deep networks in data-limited regimes has warranted much attention.
1 code implementation • 15 Feb 2024 • Arman Isajanyan, Artur Shatveryan, David Kocharyan, Zhangyang Wang, Humphrey Shi
These findings highlight the relevance and effectiveness of Social Reward in assessing community appreciation for AI-generated artworks, establishing a closer alignment with users' creative goals: creating popular visual art.
1 code implementation • 8 Jan 2021 • Ajay Kumar Jaiswal, Haoyu Ma, Tianlong Chen, Ying Ding, Zhangyang Wang
In this paper, we demonstrate that it is unnecessary for spare retraining to strictly inherit those properties from the dense network.
1 code implementation • 22 Apr 2021 • Arman Maesumi, Mingkang Zhu, Yi Wang, Tianlong Chen, Zhangyang Wang, Chandrajit Bajaj
This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes.
1 code implementation • 30 Aug 2021 • Ye Yuan, Wuyang Chen, Zhaowen Wang, Matthew Fisher, Zhifei Zhang, Zhangyang Wang, Hailin Jin
The novel graph constructor maps a glyph's latent code to its graph representation that matches expert knowledge, which is trained to help the translation task.
1 code implementation • NeurIPS 2021 • Wenqing Zheng, Qiangqiang Guo, Hao Yang, Peihao Wang, Zhangyang Wang
This paper presents the Delayed Propagation Transformer (DePT), a new transformer-based model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world.