6 citations · 24 across the 11 of their papers we have counts for
11 papers
Rethink Long-tailed Recognition with Vision Transformers
Zhengzhuo Xu, Shuo Yang, Xingjun Wang +1
In the real world, data tends to follow long-tailed distributions w.r.t. class or attribution, motivating the challenging Long-Tailed Recognition (LTR) problem. In this paper, we r…
Toward Understanding Privileged Features Distillation in Learning-to-Rank
Shuo Yang, Sujay Sanghavi, Holakou Rahmanian +2
In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised rec…
Sample Efficiency of Data Augmentation Consistency Regularization
Shuo Yang, Yijun Dong, Rachel Ward +3
Data augmentation is popular in the training of large neural networks; currently, however, there is no clear theoretical comparison between different algorithmic choices on how to…
Semantically Contrastive Learning for Low-light Image Enhancement
Dong Liang, Ling Li, Mingqiang Wei +5
Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images. In this paper, we respond to…
Does Preprocessing Help Training Over-parameterized Neural Networks?
Zhao Song, Shuo Yang, Ruizhe Zhang
Deep neural networks have achieved impressive performance in many areas. Designing a fast and provable method for training neural networks is a fundamental question in machine lear…
Speeding up Deep Model Training by Sharing Weights and Then Unsharing
Shuo Yang, Le Hou, Xiaodan Song +2
We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transfo…