most citedRobust Pre-Training by Adversarial Contrastive Learning

72 citations · 300 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV202021 cited

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

Haotao Wang, Tianlong Chen, Shupeng Gui +3

Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy. Moreover, the training process is heavy…

cs.CV202072 cited

Robust Pre-Training by Adversarial Contrastive Learning

Ziyu Jiang, Tianlong Chen, Ting Chen +1

Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-awar…

cs.CV2020

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

Prateek Shroff, Tianlong Chen, Yunchao Wei +1

Deep Neural Network has shown great strides in the coarse-grained image classification task. It was in part due to its strong ability to extract discriminative feature representati…

cs.CV2020

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

Tianlong Chen, Sijia Liu, Shiyu Chang +3

Pretrained models from self-supervision are prevalently used in fine-tuning downstream tasks faster or for better accuracy. However, gaining robustness from pretraining is left une…

cs.CV202034 cited

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

Ting-Kuei Hu, Tianlong Chen, Haotao Wang +1

Deep networks were recently suggested to face the odds between accuracy (on clean natural images) and robustness (on adversarially perturbed images) (Tsipras et al., 2019). Such a…

cs.CV20191 cited

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

Ye Yuan, Wuyang Chen, Tianlong Chen +4

Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification. However, previous ReID methods often failed to address two…