158 citations · 716 across the 49 of their papers we have counts for
5 papers · 1 filter
LAMP: Label Augmented Multimodal Pretraining
Jia Guo, Chen Zhu, Yilun Zhao +4
Multi-modal representation learning by pretraining has become an increasing interest due to its easy-to-use and potential benefit for various Visual-and-Language~(V-L) tasks. Howev…
Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation
Jia Guo, Minghao Chen, Yao Hu +3
Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the stud…
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
Wenxiao Wang, Minghao Chen, Shuai Zhao +6
Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a compu…
Do Wider Neural Networks Really Help Adversarial Robustness?
Boxi Wu, Jinghui Chen, Deng Cai +2
Adversarial training is a powerful type of defense against adversarial examples. Previous empirical results suggest that adversarial training requires wider networks for better per…
Out-of-distribution Generalization via Partial Feature Decorrelation
Xin Guo, Zhengxu Yu, Chao Xiang +5
Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribu…