Zhangyang Wang

What Does CNN Shift Invariance Look Like? A Visualization Study

Feature extraction with convolutional neural networks (CNNs) is a popula...
11/09/2020 ∙ by Jake Lee, et al. ∙ 0 ∙ share

read it
Robust Pre-Training by Adversarial Contrastive Learning

Recent work has shown that, when integrated with adversarial training, s...
10/26/2020 ∙ by Ziyu Jiang, et al. ∙ 0 ∙ share

read it
ShiftAddNet: A Hardware-Inspired Deep Network

Multiplication (e.g., convolution) is arguably a cornerstone of modern d...
10/24/2020 ∙ by Haoran You, et al. ∙ 0 ∙ share

read it
Graph Contrastive Learning with Augmentations

Generalizable, transferrable, and robust representation learning on grap...
10/22/2020 ∙ by Yuning You, et al. ∙ 13 ∙ share

read it
Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free

Adversarial training and its many variants substantially improve deep ne...
10/22/2020 ∙ by Haotao Wang, et al. ∙ 0 ∙ share

read it
Training Stronger Baselines for Learning to Optimize

Learning to optimize (L2O) has gained increasing attention since classic...
10/18/2020 ∙ by Tianlong Chen, et al. ∙ 8 ∙ share

read it
MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis

Estimating the 3D hand pose from a monocular RGB image is important but ...
10/02/2020 ∙ by Zhenyu Wu, et al. ∙ 0 ∙ share

read it
GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework

Generative adversarial networks (GANs) have gained increasing popularity...
08/25/2020 ∙ by Haotao Wang, et al. ∙ 16 ∙ share

read it
The Lottery Ticket Hypothesis for Pre-trained BERT Networks

In natural language processing (NLP), enormous pre-trained models like B...
07/23/2020 ∙ by Tianlong Chen, et al. ∙ 7 ∙ share

read it
Automated Synthetic-to-Real Generalization

Models trained on synthetic images often face degraded generalization to...
07/14/2020 ∙ by Wuyang Chen, et al. ∙ 9 ∙ share

read it
Can 3D Adversarial Logos Cloak Humans?

With the trend of adversarial attacks, researchers attempt to fool train...
06/25/2020 ∙ by Tianlong Chen, et al. ∙ 5 ∙ share

read it
When Does Self-Supervision Help Graph Convolutional Networks?

Self-supervision as an emerging technique has been employed to train con...
06/16/2020 ∙ by Yuning You, et al. ∙ 6 ∙ share

read it
AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks

The compression of Generative Adversarial Networks (GANs) has lately dra...
06/15/2020 ∙ by Yonggan Fu, et al. ∙ 42 ∙ share

read it
NADS: Neural Architecture Distribution Search for Uncertainty Awareness

Machine learning (ML) systems often encounter Out-of-Distribution (OoD) ...
06/11/2020 ∙ by Randy Ardywibowo, et al. ∙ 0 ∙ share

read it
Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification

Deep Neural Network has shown great strides in the coarse-grained image ...
05/22/2020 ∙ by Prateek Shroff, et al. ∙ 50 ∙ share

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

We present SmartExchange, an algorithm-hardware co-design framework to t...
05/07/2020 ∙ by Yang Zhao, et al. ∙ 6 ∙ share

read it
AutoSpeech: Neural Architecture Search for Speaker Recognition

Speaker recognition systems based on Convolutional Neural Networks (CNNs...
05/07/2020 ∙ by Shaojin Ding, et al. ∙ 1 ∙ share

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

Graph convolution networks (GCN) are increasingly popular in many applic...
03/30/2020 ∙ by Yuning You, et al. ∙ 0 ∙ share

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

Pretrained models from self-supervision are prevalently used in fine-tun...
03/28/2020 ∙ by Tianlong Chen, et al. ∙ 11 ∙ share

read it
Safeguarded Learned Convex Optimization

Many applications require repeatedly solving a certain type of optimizat...
03/04/2020 ∙ by Howard Heaton, et al. ∙ 0 ∙ share

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

The learning of hierarchical representations for image classification ha...
02/25/2020 ∙ by Haotao Wang, et al. ∙ 7 ∙ share

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

Deep networks were recently suggested to face the odds between accuracy ...
02/24/2020 ∙ by Ting-Kuei Hu, et al. ∙ 0 ∙ share

read it
VGAI: A Vision-Based Decentralized Controller Learning Framework for Robot Swarms

Despite the popularity of decentralized controller learning, very few su...
02/06/2020 ∙ by Ting-Kuei Hu, et al. ∙ 0 ∙ share

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

Sketch-based image editing aims to synthesize and modify photos based on...
01/09/2020 ∙ by Shuai Yang, et al. ∙ 10 ∙ share

read it
Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

While increasingly deep networks are still in general desired for achiev...
01/03/2020 ∙ by Jianghao Shen, et al. ∙ 0 ∙ share

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

Predicting compound-protein affinity is critical for accelerating drug d...
12/29/2019 ∙ by Mostafa Karimi, et al. ∙ 0 ∙ share

read it
FasterSeg: Searching for Faster Real-time Semantic Segmentation

We present FasterSeg, an automatically designed semantic segmentation ne...
12/23/2019 ∙ by Wuyang Chen, et al. ∙ 0 ∙ share

read it
Practical Solutions for Machine Learning Safety in Autonomous Vehicles

Autonomous vehicles rely on machine learning to solve challenging tasks ...
12/20/2019 ∙ by Sina Mohseni, et al. ∙ 0 ∙ share

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

The comparative losses (typically, triplet loss) are appealing choices f...
12/17/2019 ∙ by Wuyang Chen, et al. ∙ 0 ∙ share

read it
DAVID: Dual-Attentional Video Deblurring

Blind video deblurring restores sharp frames from a blurry sequence with...
12/07/2019 ∙ by Junru Wu, et al. ∙ 4 ∙ share

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

Many real-world applications, such as city-scale traffic monitoring and ...
11/26/2019 ∙ by Wuyang Chen, et al. ∙ 0 ∙ share

read it
Learning to Optimize in Swarms

Learning to optimize has emerged as a powerful framework for various opt...
11/09/2019 ∙ by Yue Cao, et al. ∙ 0 ∙ share

read it
E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving

Convolutional neural networks (CNNs) have been increasingly deployed to ...
10/29/2019 ∙ by Yue Wang, et al. ∙ 0 ∙ share

read it
Drawing early-bird tickets: Towards more efficient training of deep networks

(Frankle & Carbin, 2019) shows that there exist winning tickets (small b...
09/26/2019 ∙ by Haoran You, et al. ∙ 0 ∙ share

read it
Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach

Object detection from images captured by Unmanned Aerial Vehicles (UAVs)...
08/11/2019 ∙ by Zhenyu Wu, et al. ∙ 8 ∙ share

read it
AutoGAN: Neural Architecture Search for Generative Adversarial Networks

Neural architecture search (NAS) has witnessed prevailing success in ima...
08/11/2019 ∙ by Xinyu Gong, et al. ∙ 10 ∙ share

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

We present a new end-to-end generative adversarial network (GAN) for sin...
08/10/2019 ∙ by Orest Kupyn, et al. ∙ 6 ∙ share

read it
ABD-Net: Attentive but Diverse Person Re-Identification

Attention mechanism has been shown to be effective for person re-identif...
08/03/2019 ∙ by Tianlong Chen, et al. ∙ 4 ∙ share

read it
Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms

How can we effectively engineer a computer vision system that is able to...
07/26/2019 ∙ by Sreya Banerjee, et al. ∙ 2 ∙ share

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

State-of-the-art convolutional neural networks (CNNs) yield record-break...
07/10/2019 ∙ by Yue Wang, et al. ∙ 0 ∙ share

read it
EnlightenGAN: Deep Light Enhancement without Paired Supervision

Deep learning-based methods have achieved remarkable success in image re...
06/17/2019 ∙ by Yifan Jiang, et al. ∙ 26 ∙ share

read it
Privacy-Preserving Deep Visual Recognition: An Adversarial Learning Framework and A New Dataset

This paper aims to boost privacy-preserving visual recognition, an incre...
06/12/2019 ∙ by Haotao Wang, et al. ∙ 1 ∙ share

read it
ArcticNet: A Deep Learning Solution to Classify Arctic Wetlands

Arctic environments are rapidly changing under the warming climate. Of p...
06/01/2019 ∙ by Ziyu Jiang, et al. ∙ 0 ∙ share

read it
All-In-One Underwater Image Enhancement using Domain-Adversarial Learning

Raw underwater images are degraded due to wavelength dependent light att...
05/30/2019 ∙ by Pritish Uplavikar, et al. ∙ 0 ∙ share

read it
Segmentation-Aware Image Denoising without Knowing True Segmentation

Several recent works discussed application-driven image restoration neur...
05/22/2019 ∙ by Sicheng Wang, et al. ∙ 8 ∙ share

read it
Predicting Model Failure using Saliency Maps in Autonomous Driving Systems

While machine learning systems show high success rate in many complex ta...
05/19/2019 ∙ by Sina Mohseni, et al. ∙ 0 ∙ share

read it
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images

Segmentation of ultra-high resolution images is increasingly demanded, y...
05/15/2019 ∙ by Wuyang Chen, et al. ∙ 6 ∙ share

read it
Plug-and-Play Methods Provably Converge with Properly Trained Denoisers

Plug-and-play (PnP) is a non-convex framework that integrates modern den...
05/14/2019 ∙ by Ernest K. Ryu, et al. ∙ 9 ∙ share

read it
Controllable Artistic Text Style Transfer via Shape-Matching GAN

Artistic text style transfer is the task of migrating the style from a s...
05/03/2019 ∙ by Shuai Yang, et al. ∙ 19 ∙ share

read it
UG^2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments

The UG^2+ challenge in IEEE CVPR 2019 aims to evoke a comprehensive disc...
04/09/2019 ∙ by Wenhan Yang, et al. ∙ 0 ∙ share

read it

Zhangyang Wang

Featured Co-authors