activity
20162021
most citedKnowledge Projection for Deep Neural Networks

16 citations · 35 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CV20211 cited

Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks

Zhiqun Zhao, Hengyou Wang, Hao Sun +1

Deep neural networks recognize objects by analyzing local image details and summarizing their information along the inference layers to derive the final decision. Because of this,…

cs.CV20202 cited

Unsupervised Deep Metric Learning with Transformed Attention Consistency and Contrastive Clustering Loss

Yang Li, Shichao Kan, Zhihai He

Existing approaches for unsupervised metric learning focus on exploring self-supervision information within the input image itself. We observe that, when analyzing images, human ey…

cs.CV20201 cited

Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attacks

Jianhe Yuan, Zhihai He

Effective defense of deep neural networks against adversarial attacks remains a challenging problem, especially under powerful white-box attacks. In this paper, we develop a new me…

cs.CV20205 cited

Reciprocal Learning Networks for Human Trajectory Prediction

Hao Sun, Zhiqun Zhao, Zhihai He

We observe that the human trajectory is not only forward predictable, but also backward predictable. Both forward and backward trajectories follow the same social norms and obey th…

cs.CV2019

Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets

Yang Li, Jianhe Yuan, Zhiqun Zhao +2

In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets. We propose a master-teacher…

cs.CV2018

Progressive Neural Networks for Image Classification

Zhi Zhang, Guanghan Ning, Yigang Cen +4

The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images. However, in practice, it is…