1.6k citations · 7.3k across the 231 of their papers we have counts for
37 papers · 1 filter
Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity
Jianghao Shen, Sicheng Wang, Zhangyang Wang
Despite the latest prevailing success of deep neural networks (DNNs), several concerns have been raised against their usage, including the lack of intepretability the gap between D…
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Yonggan Fu, Haoran You, Yang Zhao +5
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such…
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Tianlong Chen, Jonathan Frankle, Shiyu Chang +4
The computer vision world has been re-gaining enthusiasm in various pre-trained models, including both classical ImageNet supervised pre-training and recently emerged self-supervis…
Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing
Junru Wu, Xiang Yu, Buyu Liu +2
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack. Due to the wide varieties of attacks, it is implausible to obt…
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…
What Does CNN Shift Invariance Look Like? A Visualization Study
Jake Lee, Junfeng Yang, Zhangyang Wang
Feature extraction with convolutional neural networks (CNNs) is a popular method to represent images for machine learning tasks. These representations seek to capture global image…