1.6k citations · 7.3k across the 231 of their papers we have counts for
10 papers · 1 filter
Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?
Nitin Bansal, Xiaohan Chen, Zhangyang Wang
This paper seeks to answer the question: as the (near-) orthogonality of weights is found to be a favorable property for training deep convolutional neural networks, how can we enf…
Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
Ding Liu, Bihan Wen, Jianbo Jiao +3
Image denoising and high-level vision tasks are usually handled independently in the conventional practice of computer vision, and their connection is fragile. In this paper, we co…
DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
Xiaofeng Zhang, Zhangyang Wang, Dong Liu +1
Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have…
U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting
Ramakrishna Prabhu, Xiaojing Yu, Zhangyang Wang +3
This paper studies the challenging problem of fingerprint image denoising and inpainting. To tackle the challenge of suppressing complicated artifacts (blur, brightness, contrast,…
Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds
Xiaohan Chen, Jialin Liu, Zhangyang Wang +1
In recent years, unfolding iterative algorithms as neural networks has become an empirical success in solving sparse recovery problems. However, its theoretical understanding is st…
Improved Techniques for Learning to Dehaze and Beyond: A Collective Study
Yu Liu, Guanlong Zhao, Boyuan Gong +8
Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level…