no code implementations • Findings (EMNLP) 2021 • Tao Huang, Hong Chen
To improve the privacy guarantee and efficiency, we combine a subsampling method with CGS and propose a novel LDA training algorithm with differential privacy, SUB-LDA.
no code implementations • 5 Feb 2025 • Jiayang Meng, Tao Huang, Xin Shi, Qingyu Huang, Chen Hou, Hong Chen
Privacy tokens encapsulate gradient features and, when combined with data features, offer valuable insights into the extent of private information leakage from training data, enabling real-time measurement of privacy risks without relying on adversarial attack simulations.
no code implementations • 4 Feb 2025 • Siyu Xu, Yunke Wang, Chenghao Xia, Dihao Zhu, Tao Huang, Chang Xu
A natural idea is to reuse the computational results of unchanged visual tokens from the last step.
no code implementations • 25 Jan 2025 • Hongwei Wen, Annika Betken, Tao Huang
On the theoretical side, we introduce the local outlier exponent to quantify the number of local outliers.
no code implementations • 14 Jan 2025 • MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu
This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens.
no code implementations • 3 Jan 2025 • Jiajun Cao, Yuan Zhang, Tao Huang, Ming Lu, Qizhe Zhang, Ruichuan An, Ningning Ma, Shanghang Zhang
Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models.
1 code implementation • 5 Dec 2024 • Xiaohuan Pei, Tao Huang, Chang Xu
KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation.
no code implementations • 1 Dec 2024 • Tao Huang, Qingyu Huang, Jiayang Meng
This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on the Degrees of Freedom (DoF) and sensitivity of intermediate outputs, without requiring adversarial attack simulations.
no code implementations • 5 Nov 2024 • Tao Huang, Jiayang Meng, Hong Chen, Guolong Zheng, Xu Yang, Xun Yi, Hua Wang
We investigate the construction of gradient-guided conditional diffusion models for reconstructing private images, focusing on the adversarial interplay between differential privacy noise and the denoising capabilities of diffusion models.
no code implementations • 5 Nov 2024 • Tao Huang, Qingyu Huang, Xin Shi, Jiayang Meng, Guolong Zheng, Xu Yang, Xun Yi
In this paper, we introduce an enhanced version of DP-SGD, named Differentially Private Per-sample Adaptive Scaling Clipping (DP-PSASC).
no code implementations • 29 Oct 2024 • Guangqi Jiang, Yifei Sun, Tao Huang, Huanyu Li, Yongyuan Liang, Huazhe Xu
Drawing from these findings, we propose Manipulation Centric Representation (MCR), a foundation representation learning framework capturing both visual features and the dynamics information such as actions and proprioceptions of manipulation tasks to improve manipulation centricity.
1 code implementation • 6 Oct 2024 • Yuan Zhang, Chun-Kai Fan, Junpeng Ma, Wenzhao Zheng, Tao Huang, Kuan Cheng, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens.
no code implementations • 5 Sep 2024 • Tao Huang
The framework suggests that for easy cases, the key is to ensure accuracy, speed and transparency, while for hard cases, what matters is reasoned justification and user participation.
no code implementations • 19 Aug 2024 • Yang Zhou, Tao Huang, Ravi Ramamoorthi, Pradeep Sen, Ling-Qi Yan
Creating an appearance-preserving level-of-detail (LoD) representation for arbitrary 3D scenes is a challenging problem.
1 code implementation • 18 Jul 2024 • Jiaqi Liu, Tao Huang, Chang Xu
Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions.
1 code implementation • 15 Jul 2024 • Hanqing Wang, Jiahe Chen, Wensi Huang, Qingwei Ben, Tai Wang, Boyu Mi, Tao Huang, Siheng Zhao, Yilun Chen, Sizhe Yang, Peizhou Cao, Wenye Yu, Zichao Ye, Jialun Li, Junfeng Long, ZiRui Wang, Huiling Wang, Ying Zhao, Zhongying Tu, Yu Qiao, Dahua Lin, Jiangmiao Pang
Recent works have been exploring the scaling laws in the field of Embodied AI.
no code implementations • 24 Jun 2024 • Tao Huang, Ziyang Chen, Jiayang Meng, Qingyu Huang, Xu Yang, Xun Yi, Ibrahim Khalil
This lightweight, scalable method significantly enhances model accuracy and strengthens resistance to membership inference attacks.
no code implementations • 13 Jun 2024 • Jiayang Meng, Tao Huang, Hong Chen, Cuiping Li
Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients.
1 code implementation • 23 May 2024 • Yuan Zhang, Fei Xiao, Tao Huang, Chun-Kai Fan, Hongyuan Dong, Jiawen Li, Jiacong Wang, Kuan Cheng, Shanghang Zhang, Haoyuan Guo
To this end, we provide a multi-modal benchmark ConBench, to intuitively analyze how LVLMs perform when the solution space of a prompt revolves around a knowledge point.
no code implementations • 21 May 2024 • Jianan Li, Tao Huang, Qingxu Zhu, Tien-Tsin Wong
To attain plausible and realistic interaction motions, our method explicitly introduces physical constraints.
no code implementations • 17 May 2024 • Tao Huang, Pengfei Chen, Kyoka Gong, Jocky Hawk, Zachary Bright, Wenxin Xie, Kecheng Huang, Zhi Ji
Since the increasing popularity of large language model (LLM) backend systems, it is common and necessary to deploy stable serverless serving of LLM on multi-GPU clusters with autoscaling.
no code implementations • 8 May 2024 • Bing Zhu, Zixin He, Weiyi Xiong, Guanhua Ding, Jianan Liu, Tao Huang, Wei Chen, Wei Xiang
However, mmWave radar relies on the collection of reflected signals from the target, and the radar signals containing information is difficult to be fully applied.
no code implementations • 28 Apr 2024 • Zeyu Hu, Yuzhi Xiao, Tao Huang, Xuanrong Huo
Sequential recommendation is one of the important branches of recommender system, aiming to achieve personalized recommended items for the future through the analysis and prediction of users' ordered historical interactive behaviors.
no code implementations • 26 Apr 2024 • Zhenrong Zhang, Jianan Liu, Xi Zhou, Tao Huang, Qing-Long Han, Jingxin Liu, Hongbin Liu
Cooperative perception is essential to enhance the efficiency and safety of future transportation systems, requiring extensive data sharing among vehicles on the road, which raises significant privacy concerns.
no code implementations • 25 Apr 2024 • Zhimeng Zheng, Tao Huang, Gongsheng Li, Zuyi Wang
In this paper, we propose a cross-architecture knowledge distillation method for MDE, dubbed DisDepth, to enhance efficient CNN models with the supervision of state-of-the-art transformer models.
no code implementations • 4 Apr 2024 • Kaixin Zhang, Zhixiang Yuan, Tao Huang
Our approach introduces a novel image generation framework that produces multi-label synthetic images of unseen classes for classifier training.
1 code implementation • 2 Apr 2024 • Quanwei Liu, Yanni Dong, Tao Huang, Lefei Zhang, Bo Du
Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap between HSI classification models between pocket models and standard vision backbones.
1 code implementation • 15 Mar 2024 • Xiaohuan Pei, Tao Huang, Chang Xu
Inspired by this, this work proposes to explore the potential of visual state space models in light-weight model design and introduce a novel efficient model variant dubbed EfficientVMamba.
1 code implementation • 14 Mar 2024 • Tao Huang, Xiaohuan Pei, Shan You, Fei Wang, Chen Qian, Chang Xu
This paper posits that the key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling.
no code implementations • 11 Mar 2024 • Tao Huang, Jiaqi Liu, Shan You, Chang Xu
Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy.
no code implementations • 11 Mar 2024 • Guanhua Ding, Jianan Liu, Yuxuan Xia, Tao Huang, Bing Zhu, Jinping Sun
Simulation results illustrate the superior estimation accuracy of the proposed PMRA-PMBM filter in terms of both positions and extents of the vehicles comparing with PMBM filters using the gamma Gaussian inverse Wishart and DRA implementations.
no code implementations • 4 Feb 2024 • Yujiao Hu, Qingmin Jia, Meng Shen, Renchao Xie, Tao Huang, F. Richard Yu
The cross-plane cooperative end-to-end routing schemes consider both computation efficiency of heterogeneous servers and the network congestion degrees while making routing plan, thereby determining where to execute requests and corresponding routing paths.
no code implementations • 31 Jan 2024 • Qingmin Jia, Yujiao Hu, Xiaomao Zhou, Qianpiao Ma, Kai Guo, Huayu Zhang, Renchao Xie, Tao Huang, Yunjie Liu
With the development of new Internet services such as computation-intensive and delay-sensitive tasks, the traditional "Best Effort" network transmission mode has been greatly challenged.
1 code implementation • 26 Jan 2024 • Qiang Zhang, Keyang Ding, Tianwen Lyv, Xinda Wang, Qingyu Yin, Yiwen Zhang, Jing Yu, Yuhao Wang, Xiaotong Li, Zhuoyi Xiang, Kehua Feng, Xiang Zhuang, Zeyuan Wang, Ming Qin, Mengyao Zhang, Jinlu Zhang, Jiyu Cui, Tao Huang, Pengju Yan, Renjun Xu, Hongyang Chen, Xiaolin Li, Xiaohui Fan, Huabin Xing, Huajun Chen
Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension, representing a significant stride toward artificial general intelligence.
1 code implementation • 22 Dec 2023 • Rongao Li, Jie Fu, Bo-Wen Zhang, Tao Huang, Zhihong Sun, Chen Lyu, Guang Liu, Zhi Jin, Ge Li
Moreover, each TACO problem includes several fine-grained labels such as task topics, algorithms, programming skills, and difficulty levels, providing a more precise reference for the training and evaluation of code generation models.
Ranked #1 on
Code Generation
on TACO-Code
1 code implementation • 21 Dec 2023 • Tao Huang, Guangqi Jiang, Yanjie Ze, Huazhe Xu
Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning (RL) tasks.
no code implementations • 20 Dec 2023 • Wenhao Li, Xiu Su, Yu Han, Shan You, Tao Huang, Chang Xu
Diffusion models have demonstrated remarkable efficacy in various generative tasks with the predictive prowess of denoising model.
1 code implementation • CVPR 2024 • Yuan Zhang, Tao Huang, Jiaming Liu, Tao Jiang, Kuan Cheng, Shanghang Zhang
(2) During the distillation period, a pixel-wise frequency mask is generated via Frequency Prompt, to localize those pixel of interests (PoIs) in various frequency bands.
no code implementations • 24 Oct 2023 • Hao Li, Quanwei Liu, Jianan Liu, Xiling Liu, Yanni Dong, Tao Huang, Zhihan Lv
To this end, we propose an unpaired MRI SR approach that employs contrastive learning to enhance SR performance with limited HR training data.
no code implementations • 5 Oct 2023 • Tao Huang, Jianan Liu, Xi Zhou, Dinh C. Nguyen, Mostafa Rahimi Azghadi, Yuxuan Xia, Qing-Long Han, Sumei Sun
Achieving fully autonomous driving with heightened safety and efficiency depends on vehicle-to-everything (V2X) cooperative perception (CP), which allows vehicles to share perception data, thereby enhancing situational awareness and overcoming the limitations of the sensing ability of individual vehicles.
1 code implementation • 18 Sep 2023 • Ting Meng, Chunyun Fu, Mingguang Huang, Xiyang Wang, JiaWei He, Tao Huang, Wankai Shi
However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified.
1 code implementation • 12 Sep 2023 • Jianan Liu, Guanhua Ding, Yuxuan Xia, Jinping Sun, Tao Huang, Lihua Xie, Bing Zhu
These provide the first benchmark and important insights for the future development of 4D imaging radar-based online 3D MOT algorithms.
1 code implementation • 12 Sep 2023 • Hao Li, Yusheng Zhou, Jianan Liu, Xiling Liu, Tao Huang, Zhihan Lyu, Weidong Cai, Wei Chen
Parallel imaging (PI) is a common approach to reduce acquisition time by periodically skipping specific k-space lines and reconstructing images from undersampled data.
no code implementations • 19 Aug 2023 • Zhenrong Zhang, Jianan Liu, Yuxuan Xia, Tao Huang, Qing-Long Han, Hongbin Liu
The state-of-the-art approaches usually employ a tracking-by-detection method, and data association plays a critical role.
1 code implementation • 31 Jul 2023 • Tao Huang, Kai Chen, Wang Wei, Jianan Li, Yonghao Long, Qi Dou
Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task.
no code implementations • 20 Jul 2023 • Jianan Liu, Qiuchi Zhao, Weiyi Xiong, Tao Huang, Qing-Long Han, Bing Zhu
Additionally, KDE helps alleviate point cloud sparsity by capturing density features.
Ranked #4 on
3D Object Detection
on View-of-Delft (val)
no code implementations • 5 Jul 2023 • Yiyao Zhou, Qianggang Wang, Yuan Chi, Jianquan Liao, Tao Huang, Niancheng Zhou, Xiaolong Xu, Xuefei Zhang
Optimal power flow (OPF) is a fundamental tool for analyzing the characteristics of bipolar DC distribution network (DCDN).
no code implementations • 3 Jul 2023 • Weiyi Xiong, Jianan Liu, Tao Huang, Qing-Long Han, Yuxuan Xia, Bing Zhu
They are sent to the core of LXL, called "radar occupancy-assisted depth-based sampling", to aid image view transformation.
Ranked #3 on
3D Object Detection (RoI)
on View-of-Delft (val)
1 code implementation • 28 Jun 2023 • Zhixiang Yuan, Kaixin Zhang, Tao Huang
Our paper addresses label noise in MLC by introducing a positive and unlabeled multi-label classification (PU-MLC) method.
no code implementations • 13 Jun 2023 • Tao Huang, Peder Bacher, Jan Kloppenborg Møller, Francesco D'Ettorre, Wiebke Brix Markussen
In addition, the model for local evaporator temperature can effectively adapt to different operational patterns and provide insight into the local cooling supply status.
1 code implementation • NeurIPS 2023 • Tao Huang, Yuan Zhang, Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Chang Xu
To address this, we propose to denoise student features using a diffusion model trained by teacher features.
Ranked #9 on
Knowledge Distillation
on ImageNet
1 code implementation • 4 May 2023 • Yuan Zhang, Weihua Chen, Yichen Lu, Tao Huang, Xiuyu Sun, Jian Cao
Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again.
2 code implementations • 20 Feb 2023 • Tao Huang, Kai Chen, Bin Li, Yun-hui Liu, Qi Dou
Task automation of surgical robot has the potentials to improve surgical efficiency.
1 code implementation • 4 Jan 2023 • Yusheng Zhou, Hao Li, Jianan Liu, Zhengmin Kong, Tao Huang, Euijoon Ahn, Zhihan Lv, Jinman Kim, David Dagan Feng
Motion artifacts compromise the quality of magnetic resonance imaging (MRI) and pose challenges to achieving diagnostic outcomes and image-guided therapies.
1 code implementation • 1 Jan 2023 • Yonghao Long, Wang Wei, Tao Huang, Yuehao Wang, Qi Dou
We showcase the improvement of our simulation environment with the designed new features, and validate effectiveness of incorporating human factors in embodied intelligence through the use of human demonstrations and reinforcement learning as a representative example.
1 code implementation • ICCV 2023 • Yunlong Liu, Tao Huang, Weisheng Dong, Fangfang Wu, Xin Li, Guangming Shi
Deep learning-based LLIE methods focus on learning a mapping function between low-light images and normal-light images that outperforms conventional LLIE methods.
no code implementations • 11 Nov 2022 • Yanlong Yang, Jianan Liu, Tao Huang, Qing-Long Han, Gang Ma, Bing Zhu
Recent state-of-the-art works reveal that the fusion of radar and LiDAR can lead to robust detection in adverse weather.
1 code implementation • CVPR 2024 • Zhengwei Fang, Rui Wang, Tao Huang, Liping Jing
Strong adversarial examples are crucial for evaluating and enhancing the robustness of deep neural networks.
1 code implementation • 12 Jul 2022 • Tao Huang, Lang Huang, Shan You, Fei Wang, Chen Qian, Chang Xu
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias.
1 code implementation • 21 Jun 2022 • Jianan Liu, Liping Bai, Yuxuan Xia, Tao Huang, Bing Zhu, Qing-Long Han
The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry.
no code implementations • 30 May 2022 • Chengfei Lv, Chaoyue Niu, Renjie Gu, Xiaotang Jiang, Zhaode Wang, Bin Liu, Ziqi Wu, Qiulin Yao, Congyu Huang, Panos Huang, Tao Huang, Hui Shu, Jinde Song, Bin Zou, Peng Lan, Guohuan Xu, Fei Wu, Shaojie Tang, Fan Wu, Guihai Chen
Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.
1 code implementation • 29 May 2022 • Tao Huang, Yuan Zhang, Shan You, Fei Wang, Chen Qian, Jian Cao, Chang Xu
To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks.
3 code implementations • 21 May 2022 • Tao Huang, Shan You, Fei Wang, Chen Qian, Chang Xu
In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly.
Ranked #9 on
Knowledge Distillation
on CIFAR-100
no code implementations • 13 May 2022 • Jianan Liu, Hao Li, Tao Huang, Euijoon Ahn, Kang Han, Adeel Razi, Wei Xiang, Jinman Kim, David Dagan Feng
However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.
2 code implementations • CVPR 2022 • Tao Huang, Shan You, Bohan Zhang, Yuxuan Du, Fei Wang, Chen Qian, Chang Xu
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks.
no code implementations • 13 Mar 2022 • Weiyi Xiong, Jianan Liu, Yuxuan Xia, Tao Huang, Bing Zhu, Wei Xiang
Deep learning-based instance segmentation enables real-time object identification from the radar detection points.
1 code implementation • ICLR 2022 • Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e. g., average precision and F1 score.
no code implementations • 18 Jan 2022 • Tao Huang, Jiachen Wang, Xiao Chen
Learning informative representations from image-based observations is of fundamental concern in deep Reinforcement Learning (RL).
no code implementations • 28 Nov 2021 • Hao Li, Jianan Liu, Marianne Schell, Tao Huang, Arne Lauer, Katharina Schregel, Jessica Jesser, Dominik F Vollherbst, Martin Bendszus, Sabine Heiland, Tim Hilgenfeld
Deep learning-based image restoration has emerged as a promising solution capable of generating high-resolution and motion-artifact-free MRI images from low-resolution images acquired with shortened acquisition times or from motion-artifact-corrupted images.
no code implementations • CVPR 2022 • Tao Huang, Shan You, Fei Wang, Chen Qian, ChangShui Zhang, Xiaogang Wang, Chang Xu
In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently.
no code implementations • 5 Oct 2021 • Jianan Liu, Weiyi Xiong, Liping Bai, Yuxuan Xia, Tao Huang, Wanli Ouyang, Bing Zhu
Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points.
no code implementations • 29 Sep 2021 • Tao Huang, Xiao Chen, Jiachen Wang
Learning informative representations from image-based observations is a fundamental problem in deep Reinforcement Learning (RL).
no code implementations • 3 Jun 2021 • Hanyuan Hang, Tao Huang, Yuchao Cai, Hanfang Yang, Zhouchen Lin
In this paper, we propose a gradient boosting algorithm for large-scale regression problems called \textit{Gradient Boosted Binary Histogram Ensemble} (GBBHE) based on binary histogram partition and ensemble learning.
1 code implementation • CVPR 2021 • Xiu Su, Tao Huang, Yanxi Li, Shan You, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu
One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once.
1 code implementation • CVPR 2021 • Tao Huang, Weisheng Dong, Xin Yuan, Jinjian Wu, Guangming Shi
Different from existing GSM models using hand-crafted scale priors (e. g., the Jeffrey's prior), we propose to learn the scale prior through a deep convolutional neural network (DCNN).
no code implementations • ICLR 2021 • Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu
In this paper, to better evaluate each width, we propose a locally free weight sharing strategy (CafeNet) accordingly.
12 code implementations • CVPR 2021 • Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, Jianzhuang Liu
In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.
no code implementations • 1 Jan 2021 • Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang
Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types.
no code implementations • 1 Jan 2021 • Zhuozhuo Tu, Shan You, Tao Huang, DaCheng Tao
Wasserstein distributionally robust optimization (DRO) has recently received significant attention in machine learning due to its connection to generalization, robustness and regularization.
no code implementations • 18 Nov 2020 • Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang
However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells.
no code implementations • 17 Nov 2020 • Tao Huang, Yihan Zhang, Jiajing Wu, Junyuan Fang, Zibin Zheng
To tackle the dilemma between accuracy and efficiency, we propose to use aggregators with different granularities to gather neighborhood information in different layers.
no code implementations • 28 Oct 2020 • Xiu Su, Shan You, Tao Huang, Hongyan Xu, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu
To deploy a well-trained CNN model on low-end computation edge devices, it is usually supposed to compress or prune the model under certain computation budget (e. g., FLOPs).
1 code implementation • 20 Oct 2020 • Yuxuan Du, Tao Huang, Shan You, Min-Hsiu Hsieh, DaCheng Tao
Variational quantum algorithms (VQAs) are expected to be a path to quantum advantages on noisy intermediate-scale quantum devices.
no code implementations • CVPR 2020 • Shan You, Tao Huang, Mingmin Yang, Fei Wang, Chen Qian, Chang-Shui Zhang
The training efficiency is thus boosted since the training space has been greedily shrunk from all paths to those potentially-good ones.
Ranked #72 on
Neural Architecture Search
on ImageNet
no code implementations • ICLR 2020 • Tao Huang, Zhen Han, Xu Jia, Hanyuan Hang
In this paper, we propose a novel kind of kernel, random forest kernel, to enhance the empirical performance of MMD GAN.
no code implementations • 20 Dec 2019 • Shujie Han, Jun Wu, Erci Xu, Cheng He, Patrick P. C. Lee, Yi Qiang, Qixing Zheng, Tao Huang, Zixi Huang, Rui Li
To provide proactive fault tolerance for modern cloud data centers, extensive studies have proposed machine learning (ML) approaches to predict imminent disk failures for early remedy and evaluated their approaches directly on public datasets (e. g., Backblaze SMART logs).