activity
20162022
most citedHow does Disagreement Help Generalization against Label Corruption?

154 citations · 418 across the 22 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV20222 cited

NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension

Xin He, Jiangchao Yao, Yuxin Wang +5

One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i.…

cs.CV2022

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

Xiaobo Xia, Wenhao Yang, Jie Ren +4

Pluralistic image completion focuses on generating both visually realistic and diverse results for image completion. Prior methods enjoy the empirical successes of this task. Howev…

cs.CV202115 cited

Towards Defending against Adversarial Examples via Attack-Invariant Features

Dawei Zhou, Tongliang Liu, Bo Han +3

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously ev…

cs.CV20201 cited

Confusable Learning for Large-class Few-Shot Classification

Bingcong Li, Bo Han, Zhuowei Wang +2

Few-shot image classification is challenging due to the lack of ample samples in each class. Such a challenge becomes even tougher when the number of classes is very large, i.e., t…

cs.CV201913 cited

Towards Robust ResNet: A Small Step but A Giant Leap

Jingfeng Zhang, Bo Han, Laura Wynter +2

This paper presents a simple yet principled approach to boosting the robustness of the residual network (ResNet) that is motivated by the dynamical system perspective. Namely, a de…