Search Results for author: Zhangyang Wang

Found 218 papers, 126 papers with code

Eliminating the Invariance on the Loss Landscape of Linear Autoencoders

no code implementations ICML 2020 Reza Oftadeh, Jiayi Shen, Zhangyang Wang, Dylan Shell

For this new loss, we characterize the full structure of the loss landscape in the following sense: we establish analytical expression for the set of all critical points, show that it is a subset of critical points of MSE, and that all local minima are still global.

HALO: Hardware-Aware Learning to Optimize

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.

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

1 code implementation11 May 2022 Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex.

Neural Architecture Search

Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN

1 code implementation27 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.

Disentanglement Face Generation

E^2TAD: An Energy-Efficient Tracking-based Action Detector

no code implementations9 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.

Fine-Grained Action Detection Frame +3

Unified Implicit Neural Stylization

no code implementations5 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.

Neural Stylization Novel View Synthesis

APP: Anytime Progressive Pruning

1 code implementation4 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.

Network Pruning online learning

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

no code implementations2 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.

Novel View Synthesis

VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition

no code implementations31 Mar 2022 Randy Ardywibowo, Shahin Boluki, Zhangyang Wang, Bobak Mortazavi, Shuai Huang, Xiaoning Qian

At its core is an implicit variational distribution on binary gates that are dependent on previous observations, which will select the next subset of features to observe.

Activity Recognition

On the Neural Tangent Kernel Analysis of Randomly Pruned Wide Neural Networks

no code implementations27 Mar 2022 Hongru Yang, Zhangyang Wang

We show that for fully-connected neural networks when the network is pruned randomly at the initialization, as the width of each layer grows to infinity, the empirical NTK of the pruned neural network converges to that of the original (unpruned) network with some extra scaling factor.

Image Classification

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

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.

Personalized Federated Learning

Symbolic Learning to Optimize: Towards Interpretability and Scalability

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.

Optimizer Amalgamation

1 code implementation ICLR 2022 Tianshu Huang, Tianlong Chen, Sijia Liu, Shiyu Chang, Lisa Amini, Zhangyang Wang

Selecting an appropriate optimizer for a given problem is of major interest for researchers and practitioners.

The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy

1 code implementation12 Mar 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.

Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice

1 code implementation9 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.

Auto-scaling Vision Transformers without Training

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.

Sparsity Winning Twice: Better Robust Generalization from More Efficient Training

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.

Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets

1 code implementation9 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.

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

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.

Adversarial Robustness Out-of-Distribution Detection

VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer

no code implementations17 Jan 2022 Mengshu Sun, Haoyu Ma, Guoliang Kang, Yifan Jiang, Tianlong Chen, Xiaolong Ma, Zhangyang Wang, Yanzhi Wang

To the best of our knowledge, this is the first time quantization has been incorporated into ViT acceleration on FPGAs with the help of a fully automatic framework to guide the quantization strategy on the software side and the accelerator implementations on the hardware side given the target frame rate.

Frame Quantization

Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations

1 code implementation4 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.

Contrastive Learning Graph Learning

Fast and High-Quality Image Denoising via Malleable Convolutions

no code implementations2 Jan 2022 Yifan Jiang, Bart Wronski, Ben Mildenhall, Jon Barron, Zhangyang Wang, Tianfan Xue

To achieve spatial-varying processing without significant overhead, we present Malleable Convolution (MalleConv), as an efficient variant of dynamic convolution.

Image Denoising Image Restoration

Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better

1 code implementation18 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.

Federated Learning

A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation

no code implementations17 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.

Image Classification Instance Segmentation +3

Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling

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.

Contrastive Learning

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

1 code implementation30 Oct 2021 Xuxi Chen, Tianlong Chen, Yu Cheng, Weizhu Chen, Zhangyang Wang, Ahmed Hassan Awadallah

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.

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership

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.

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

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.

Hyperparameter Tuning is All You Need for LISTA

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.

Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis

1 code implementation9 Oct 2021 Mu Yang, Shaojin Ding, Tianlong Chen, Tong Wang, Zhangyang Wang

This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually.

Speech Synthesis Text-To-Speech Synthesis

Universality of Winning Tickets: A Renormalization Group Perspective

no code implementations7 Oct 2021 William T. Redman, Tianlong Chen, Zhangyang Wang, Akshunna S. Dogra

We make use of renormalization group theory, a powerful tool from theoretical physics, to address this need.

CheXT: Knowledge-Guided Cross-Attention Transformer for Abnormality Classification and Localization in Chest X-rays

no code implementations29 Sep 2021 Yan Han, Ying Ding, Ahmed Tewfik, Yifan Peng, Zhangyang Wang

During training, the image branch leverages its learned attention to estimate pathology localization, which is then utilized to extract radiomic features from images in the radiomics branch.

Reasoning With Hierarchical Symbols: Reclaiming Symbolic Policies For Visual Reinforcement Learning

no code implementations29 Sep 2021 Wenqing Zheng, S P Sharan, Zhiwen Fan, Zhangyang Wang

Deep vision models are nowadays widely integrated into visual reinforcement learning (RL) to parameterize the policy networks.

reinforcement-learning

Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable

no code implementations ICLR 2022 Shaojin Ding, Tianlong Chen, Zhangyang Wang

In this paper, we investigate the tantalizing possibility of using lottery ticket hypothesis to discover lightweight speech recognition models, that are (1) robust to various noise existing in speech; (2) transferable to fit the open-world personalization; and 3) compatible with structured sparsity.

Speech Recognition

Universality of Deep Neural Network Lottery Tickets: A Renormalization Group Perspective

no code implementations29 Sep 2021 William T Redman, Tianlong Chen, Akshunna S. Dogra, Zhangyang Wang

Foundational work on the Lottery Ticket Hypothesis has suggested an exciting corollary: winning tickets found in the context of one task can be transferred to similar tasks, possibly even across different architectures.

Lottery Tickets can have Structural Sparsity

no code implementations29 Sep 2021 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., $\textit{winning tickets}$) that can be trained in isolation to match full accuracy.

Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining

no code implementations 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.

Equalized Robustness: Towards Sustainable Fairness Under Distributional Shifts

no code implementations29 Sep 2021 Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang

In this paper, we first propose a new fairness goal, termed Equalized Robustness (ER), to impose fair model robustness against unseen distribution shifts across majority and minority groups.

Fairness

Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How

no code implementations ICLR 2022 Yuning You, Yue Cao, Tianlong Chen, Zhangyang Wang, Yang shen

Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions.

Variational Inference

Generalizable Learning to Optimize into Wide Valleys

no code implementations29 Sep 2021 Junjie Yang, Tianlong Chen, Mingkang Zhu, Fengxiang He, DaCheng Tao, Yingbin Liang, Zhangyang Wang

Learning to optimize (L2O) has gained increasing popularity in various optimization tasks, since classical optimizers usually require laborious, problem-specific design and hyperparameter tuning.

Scaling the Depth of Vision Transformers via the Fourier Domain Analysis

no code implementations ICLR 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.

Lottery Image Prior

no code implementations29 Sep 2021 Qiming Wu, Xiaohan Chen, Yifan Jiang, Pan Zhou, Zhangyang Wang

Drawing inspirations from the recently prosperous research on lottery ticket hypothesis (LTH), we conjecture and study a novel “lottery image prior” (LIP), stated as: given an (untrained or trained) DNN-based image prior, it will have a sparse subnetwork that can be training in isolation, to match the original DNN’s performance when being applied as a prior to various image inverse problems.

Compressive Sensing Image Reconstruction +1

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently

no code implementations ICLR 2022 Xiaohan Chen, Jason Zhang, Zhangyang Wang

In this work, we define an extended class of subnetworks in randomly initialized NNs called disguised subnetworks, which are not only "hidden" in the random networks but also "disguised" -- hence can only be "unmasked" with certain transformations on weights.

Stingy Teacher: Sparse Logits Suffice to Fail Knowledge Distillation

no code implementations29 Sep 2021 Haoyu Ma, Yifan Huang, Tianlong Chen, Hao Tang, Chenyu You, Zhangyang Wang, Xiaohui Xie

However, it is unclear why the distorted distribution of the logits is catastrophic to the student model.

Knowledge Distillation

AutoCoG: A Unified Data-Modal Co-Search Framework for Graph Neural Networks

no code implementations29 Sep 2021 Duc N.M Hoang, Kaixiong Zhou, Tianlong Chen, Xia Hu, Zhangyang Wang

Despite the preliminary success, we argue that for GNNs, NAS has to be customized further, due to the topological complicacy of GNN input data (graph) as well as the notorious training instability.

Data Augmentation Language Modelling +1

GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization

no code implementations ICCV 2021 Yi Guo, Huan Yuan, Jianchao Tan, Zhangyang Wang, Sen yang, Ji Liu

During the training process, the polarization effect will drive a subset of gates to smoothly decrease to exact zero, while other gates gradually stay away from zero by a large margin.

Model Compression Network Pruning

Font Completion and Manipulation by Cycling Between Multi-Modality Representations

1 code implementation30 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.

Image-to-Image Translation Representation Learning +2

Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics

1 code implementation26 Aug 2021 Wuyang Chen, Xinyu Gong, 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.

Neural Architecture Search

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study

1 code implementation24 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.

SSH: A Self-Supervised Framework for Image Harmonization

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.

Data Augmentation

CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise

1 code implementation1 Aug 2021 Zeyuan Chen, Yifan Jiang, Dong Liu, Zhangyang Wang

We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework.

Denoising

Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study

1 code implementation23 Jul 2021 Zhenyu Wu, Zhaowen Wang, Ye Yuan, Jianming Zhang, Zhangyang Wang, Hailin Jin

Existing diversity tests of samples from GANs are usually conducted qualitatively on a small scale, and/or depends on the access to original training data as well as the trained model parameters.

Image Generation

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference

no code implementations16 Jul 2021 Chaojian Li, Wuyang Chen, Yuchen Gu, Tianlong Chen, Yonggan Fu, Zhangyang Wang, Yingyan Lin

Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms.

Scene Understanding Semantic Segmentation

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

1 code implementation 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.

Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks

1 code implementation24 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.

Imitation Learning

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers

no code implementations NeurIPS 2021 Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang, Rogerio Feris, Aude Oliva

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision.

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

1 code implementation 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).

Network Pruning Sparse Learning

Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning

no code implementations18 Jun 2021 Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou

In this paper, we study a novel learning setting that propagates adversarial robustness from high-resource users that can afford AT, to those low-resource users that cannot afford it, during the FL process.

Adversarial Robustness Federated Learning

Graph Contrastive Learning Automated

2 code implementations10 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.

Contrastive Learning Representation Learning +1

Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm

1 code implementation10 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.

Adversarial Attack

Taxonomy of Machine Learning Safety: A Survey and Primer

no code implementations9 Jun 2021 Sina Mohseni, Haotao Wang, Zhiding Yu, Chaowei Xiao, Zhangyang Wang, Jay Yadawa

The open-world deployment of Machine Learning (ML) algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities such as interpretability, verifiability, and performance limitations.

Autonomous Vehicles Domain Adaptation

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

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.

Self-Damaging Contrastive Learning

1 code implementation6 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.

Contrastive Learning Network Pruning +1

Efficient Lottery Ticket Finding: Less Data is More

1 code implementation6 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.

Improving Contrastive Learning on Imbalanced Data via Open-World Sampling

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.

Contrastive Learning

Undistillable: Making A Nasty Teacher That CANNOT teach students

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.

Knowledge Distillation

Troubleshooting Blind Image Quality Models in the Wild

no code implementations CVPR 2021 Zhihua Wang, Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma

Recently, the group maximum differentiation competition (gMAD) has been used to improve blind image quality assessment (BIQA) models, with the help of full-reference metrics.

Blind Image Quality Assessment Network Pruning

SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization

1 code implementation13 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.

Style Transfer

InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks

1 code implementation22 Apr 2021 Yonggan Fu, Zhongzhi Yu, Yongan Zhang, Yifan Jiang, Chaojian Li, Yongyuan Liang, Mingchao Jiang, Zhangyang Wang, Yingyan Lin

The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices.

Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors

1 code implementation22 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.

Adversarial Attack

"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization

1 code implementation16 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.

Image Classification

Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop

no code implementations11 Apr 2021 Yan Han, Chongyan Chen, Ahmed Tewfik, Benjamin Glicksberg, Ying Ding, Yifan Peng, Zhangyang Wang

The key knob of our framework is a unique positive sampling approach tailored for the medical images, by seamlessly integrating radiomic features as a knowledge augmentation.

Contrastive Learning

A Design Space Study for LISTA and Beyond

no code implementations ICLR 2021 Tianjian Meng, Xiaohan Chen, Yifan Jiang, Zhangyang Wang

Unrolling is believed to incorporate the model-based prior with the learning capacity of deep learning.

Neural Architecture Search

Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data

no code implementations7 Apr 2021 Tingyi Wanyan, Jing Zhang, Ying Ding, Ariful Azad, Zhangyang Wang, Benjamin S Glicksberg

Electronic Health Record (EHR) data has been of tremendous utility in Artificial Intelligence (AI) for healthcare such as predicting future clinical events.

Contrastive Learning Data Augmentation

The Elastic Lottery Ticket Hypothesis

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.

UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution

1 code implementation23 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 spatial coordinates and periodic encoding are deeply integrated with the implicit neural representation.

Super-Resolution

Learning to Optimize: A Primer and A Benchmark

1 code implementation23 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.

Adversarial Feature Augmentation and Normalization for Visual Recognition

1 code implementation22 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.

Classification Data Augmentation +1

Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective

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.

Data Augmentation

Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition

1 code implementation27 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?

Semantic Segmentation

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective

3 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?

Neural Architecture Search

Stronger NAS with Weaker Predictors

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.

Neural Architecture Search

TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up

9 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.

Data Augmentation Image Generation

A Unified Lottery Ticket Hypothesis for Graph Neural Networks

1 code implementation12 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.

Link Prediction Node Classification

On Dynamic Noise Influence in Differentially Private Learning

no code implementations19 Jan 2021 Junyuan Hong, Zhangyang Wang, Jiayu Zhou

In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.

Spending Your Winning Lottery Better After Drawing It

1 code implementation8 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.

Knowledge Distillation

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

1 code implementation4 Jan 2021 Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang

Results show that: 1) applied to inference, SD achieves up to 2. 44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10. 56x and 4. 48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines.

Bayesian Learning to Optimize: Quantifying the Optimizer Uncertainty

no code implementations1 Jan 2021 Yue Cao, Tianlong Chen, Zhangyang Wang, Yang shen

Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions.

Image Classification Variational Inference

Weak NAS Predictor Is All You Need

no code implementations1 Jan 2021 Junru Wu, Xiyang Dai, Dongdong Chen, Yinpeng Chen, Mengchen Liu, Ye Yu, Zhangyang Wang, Zicheng Liu, Mei Chen, Lu Yuan

Rather than expecting a single strong predictor to model the whole space, we seek a progressive line of weak predictors that can connect a path to the best architecture, thus greatly simplifying the learning task of each predictor.

Neural Architecture Search

Efficiently Troubleshooting Image Segmentation Models with Human-In-The-Loop

no code implementations1 Jan 2021 Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma

Image segmentation lays the foundation for many high-stakes vision applications such as autonomous driving and medical image analysis.

Autonomous Driving Semantic Segmentation

On Dynamic Noise Influence in Differential Private Learning

no code implementations1 Jan 2021 Junyuan Hong, Zhangyang Wang, Jiayu Zhou

In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.

ALFA: Adversarial Feature Augmentation for Enhanced Image Recognition

no code implementations1 Jan 2021 Tianlong Chen, Yu Cheng, Zhe Gan, Yu Hu, Zhangyang Wang, Jingjing Liu

Adversarial training is an effective method to combat adversarial attacks in order to create robust neural networks.

Learning A Minimax Optimizer: A Pilot Study

no code implementations ICLR 2021 Jiayi Shen, Xiaohan Chen, Howard Heaton, Tianlong Chen, Jialin Liu, Wotao Yin, Zhangyang Wang

We first present Twin L2O, the first dedicated minimax L2O framework consisting of two LSTMs for updating min and max variables, respectively.

Robust Overfitting may be mitigated by properly learned smoothening

no code implementations ICLR 2021 Tianlong Chen, Zhenyu Zhang, Sijia Liu, Shiyu Chang, Zhangyang Wang

A recent study (Rice et al., 2020) revealed overfitting to be a dominant phenomenon in adversarially robust training of deep networks, and that appropriate early-stopping of adversarial training (AT) could match the performance gains of most recent algorithmic improvements.

Knowledge Distillation

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

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.

Model Compression

Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity

no code implementations29 Dec 2020 Jianghao Shen, Sicheng Wang, Zhangyang Wang

For example, our model with only 1 layer of 15 trees can perform comparably with the model in [3] with 2 layers of 2000 trees each.

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training

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.

Quantization

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

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.

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

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.

Few-Shot Learning

What Does CNN Shift Invariance Look Like? A Visualization Study

1 code implementation9 Nov 2020 Jake Lee, Junfeng Yang, Zhangyang Wang

We present the results of three experiments comparing representations of millions of images with exhaustively shifted objects, examining both local invariance (within a few pixels) and global invariance (across the image frame).

Frame

Robust Pre-Training by Adversarial Contrastive Learning

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.

Adversarial Robustness Contrastive Learning

Graph Contrastive Learning with Augmentations

2 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.

Contrastive Learning Representation Learning +2

Training Stronger Baselines for Learning to Optimize

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.

Imitation Learning

PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning

no code implementations6 Oct 2020 Yuli Zheng, Zhenyu Wu, Ye Yuan, Tianlong Chen, Zhangyang Wang

While machine learning is increasingly used in this field, the resulting large-scale collection of user private information has reinvigorated the privacy debate, considering dozens of data breach incidents every year caused by unauthorized hackers, and (potentially even more) information misuse/abuse by authorized parties.

GAN Slimming: All-in-One GAN Compression by A Unified Optimization 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.

Image-to-Image Translation Quantization +1

AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation

no code implementations16 Aug 2020 Xinyu Gong, Wuyang Chen, Yifan Jiang, Ye Yuan, Xian-Ming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations.

Neural Architecture Search Pose Estimation

Can 3D Adversarial Logos Cloak Humans?

1 code implementation25 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.

Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training

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.

When Does Self-Supervision Help Graph Convolutional Networks?

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.

Multi-Task Learning Representation Learning +1

AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks

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.

AutoML Knowledge Distillation +2

NADS: Neural Architecture Distribution Search for Uncertainty Awareness

no code implementations ICML 2020 Randy Ardywibowo, Shahin Boluki, Xinyu Gong, Zhangyang Wang, Xiaoning Qian

Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data.

OOD Detection

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

no code implementations7 May 2020 Yang Zhao, Xiaohan Chen, Yue Wang, Chaojian Li, Haoran You, Yonggan Fu, Yuan Xie, Zhangyang Wang, Yingyan Lin

We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs).

Model Compression Quantization

AutoSpeech: Neural Architecture Search for Speaker Recognition

3 code implementations7 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.

Image Classification Neural Architecture Search +3

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks

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.

L^2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

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.

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

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.

Adversarial Robustness

Safeguarded Learned Convex Optimization

no code implementations4 Mar 2020 Howard Heaton, Xiaohan Chen, Zhangyang Wang, Wotao Yin

Many applications require repeatedly solving a certain type of optimization problem, each time with new (but similar) data.

Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery

no code implementations3 Mar 2020 Zepeng Huo, Arash Pakbin, Xiaohan Chen, Nathan Hurley, Ye Yuan, Xiaoning Qian, Zhangyang Wang, Shuai Huang, Bobak Mortazavi

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm.

Activity Recognition

I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively

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.

Image Classification

Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference

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).

VGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms

no code implementations6 Feb 2020 Ting-Kuei Hu, Fernando Gama, Tianlong Chen, Zhangyang Wang, Alejandro Ribeiro, Brian M. Sadler

More specifically, we consider that each robot has access to a visual perception of the immediate surroundings, and communication capabilities to transmit and receive messages from other neighboring robots.

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches

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.

Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

1 code implementation3 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.

Quantization

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts

no code implementations29 Dec 2019 Mostafa Karimi, Di wu, Zhangyang Wang, Yang shen

DeepRelations shows superior interpretability to the state-of-the-art: without compromising affinity prediction, it boosts the AUPRC of contact prediction 9. 5, 16. 9, 19. 3 and 5. 7-fold for the test, compound-unique, protein-unique, and both-unique sets, respectively.

Drug Discovery Interpretable Machine Learning

FasterSeg: Searching for Faster Real-time Semantic Segmentation

1 code implementation 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.

Neural Architecture Search Real-Time Semantic Segmentation

Practical Solutions for Machine Learning Safety in Autonomous Vehicles

no code implementations20 Dec 2019 Sina Mohseni, Mandar Pitale, Vasu Singh, Zhangyang Wang

Autonomous vehicles rely on machine learning to solve challenging tasks in perception and motion planning.

Autonomous Vehicles Motion Planning

In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation

1 code implementation17 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.

Person Re-Identification

DAVID: Dual-Attentional Video Deblurring

no code implementations7 Dec 2019 Junru Wu, Xiang Yu, Ding Liu, Manmohan Chandraker, Zhangyang Wang

To train and evaluate on more diverse blur severity levels, we propose a Challenging DVD dataset generated from the raw DVD video set by pooling frames with different temporal windows.

Deblurring Frame

Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification

1 code implementation26 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.

Learning to Optimize in Swarms

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.

E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings

no code implementations NeurIPS 2019 Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang

Extensive simulations and ablation studies, with real energy measurements from an FPGA board, confirm the superiority of our proposed strategies and demonstrate remarkable energy savings for training.

Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks

1 code implementation26 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.

Universal Safeguarded Learned Convex Optimization with Guaranteed Convergence

no code implementations25 Sep 2019 Howard Heaton, Xiaohan Chen, Zhangyang Wang, Wotao Yin

Inferences by each network form solution estimates, and networks are trained to optimize these estimates for a particular distribution of data.

Neural Networks for Principal Component Analysis: A New Loss Function Provably Yields Ordered Exact Eigenvectors

no code implementations25 Sep 2019 Reza Oftadeh, Jiayi Shen, Zhangyang Wang, Dylan Shell

In this paper, we propose a new loss function for performing principal component analysis (PCA) using linear autoencoders (LAEs).

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better

4 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.

Blind Face Restoration Image Deblurring +2

Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference

no code implementations10 Jul 2019 Yue Wang, Jianghao Shen, Ting-Kuei Hu, Pengfei Xu, Tan Nguyen, Richard Baraniuk, Zhangyang Wang, Yingyan Lin

State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications.

EnlightenGAN: Deep Light Enhancement without Paired Supervision

8 code implementations17 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?

Image Restoration Low-Light Image Enhancement

Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset

5 code implementations12 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.

Action Recognition Privacy Preserving Deep Learning

Segmentation-Aware Image Denoising without Knowing True Segmentation

2 code implementations22 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.

Image Denoising Image Restoration +1