activity
20182022
most citedZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

34 citations · 174 across the 23 of their papers we have counts for

collaborators

53 papers

eess.IV20223 cited

Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System

Xin Li, Yao Qiang, Chengyin Li +2

This work tackles a central machine learning problem of performance degradation on out-of-distribution (OOD) test sets. The problem is particularly salient in medical imaging based…

cs.CV20228 cited

Reverse Engineering of Imperceptible Adversarial Image Perturbations

Yifan Gong, Yuguang Yao, Yize Li +4

It has been well recognized that neural network based image classifiers are easily fooled by images with tiny perturbations crafted by an adversary. There has been a vast volume of…

cs.LG20221 cited

How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis

Shuai Zhang, Meng Wang, Sijia Liu +2

Self-training, a semi-supervised learning algorithm, leverages a large amount of unlabeled data to improve learning when the labeled data are limited. Despite empirical successes,…

cs.LG20222 cited

Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework

Ching-Yun Ko, Jeet Mohapatra, Sijia Liu +3

As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leve…

cs.CV20216 cited

When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?

Lijie Fan, Sijia Liu, Pin-Yu Chen +2

Contrastive learning (CL) can learn generalizable feature representations and achieve the state-of-the-art performance of downstream tasks by finetuning a linear classifier on top…

cs.LG2021

Certifiably Robust Interpretation via Renyi Differential Privacy

Ao Liu, Xiaoyu Chen, Sijia Liu +2

Motivated by the recent discovery that the interpretation maps of CNNs could easily be manipulated by adversarial attacks against network interpretability, we study the problem of…