10 citations · 21 across the 8 of their papers we have counts for
8 papers
Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective
Wanying Wang, Yichen Zhu, Yirui Zhou +5
Generative Adversarial Imitation Learning (GAIL) stands as a cornerstone approach in imitation learning. This paper investigates the gradient explosion in two types of GAIL: GAIL w…
Recognizable Information Bottleneck
Yilin Lyu, Xin Liu, Mingyang Song +4
Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalizat…
CP: Channel Pruning Plug-in for Point-based Networks
Yaomin Huang, Ning Liu, Zhengping Che +7
Channel pruning can effectively reduce both computational cost and memory footprint of the original network while keeping a comparable accuracy performance. Though great success ha…
Label-Guided Auxiliary Training Improves 3D Object Detector
Yaomin Huang, Xinmei Liu, Yichen Zhu +7
Detecting 3D objects from point clouds is a practical yet challenging task that has attracted increasing attention recently. In this paper, we propose a Label-Guided auxiliary trai…
Hybrid Atlas Building with Deep Registration Priors
Nian Wu, Jian Wang, Miaomiao Zhang +3
Registration-based atlas building often poses computational challenges in high-dimensional image spaces. In this paper, we introduce a novel hybrid atlas building algorithm that fa…
Efficient Robust Watermarking Based on Quaternion Singular Value Decomposition and Coefficient Pair Selection
Yong Chen, Zhi-Gang Jia, Ya-Xin Peng +1
Quaternion singular value decomposition (QSVD) is a robust technique of digital watermarking which can extract high quality watermarks from watermarked images with low distortion.…
Defending Against Adversarial Attacks by Suppressing the Largest Eigenvalue of Fisher Information Matrix
Chaomin Shen, Yaxin Peng, Guixu Zhang +1
We propose a scheme for defending against adversarial attacks by suppressing the largest eigenvalue of the Fisher information matrix (FIM). Our starting point is one explanation on…
The Adversarial Attack and Detection under the Fisher Information Metric
Chenxiao Zhao, P. Thomas Fletcher, Mixue Yu +3
Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the netw…