553 citations
- Beihang UniversityCN66 papers
- Microsoft Research Asia (China)CN12 papers
- Chinese Academy of SciencesCN9 papers
- Tsinghua UniversityCN6 papers
- National Cheng Kung UniversityTW4 papers
- University of Chinese Academy of SciencesCN4 papers
- Institute of SoftwareCN3 papers
- Zhejiang UniversityCN3 papers
- CAS Key Laboratory of Quantum Information, USTCCN2 papers
- Nankai UniversityCN2 papers
- State Key Laboratory of Computer Science2 papers
- State Key Laboratory of Low-Dimensional Quantum Physics2 papers
5 papers · 2 filters
Balanced Binary Neural Networks with Gated Residual
Mingzhu Shen, Xianglong Liu, Ruihao Gong +1
Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the acc…
Forward and Backward Information Retention for Accurate Binary Neural Networks
Haotong Qin, Ruihao Gong, Xianglong Liu +4
Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many bina…
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
Chongzhi Zhang, Aishan Liu, Xianglong Liu +4
Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they…
Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
Youmin Zhang, Yimin Chen, Xiao Bai +4
State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and…
Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network
Shengyu Zhao, Tingfung Lau, Ji Luo +2
3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or…