activity
20162021
most citedSCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses

85 citations · 248 across the 18 of their papers we have counts for

collaborators

34 papers

cs.CV202123 cited

Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey

Ngan Le, Vidhiwar Singh Rathour, Kashu Yamazaki +2

Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remar…

cs.LG202126 cited

Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study

Zhiqiang Shen, Zechun Liu, Dejia Xu +3

This work aims to empirically clarify a recently discovered perspective that label smoothing is incompatible with knowledge distillation. We begin by introducing the motivation beh…

cs.CV20211 cited

Unsupervised Disentanglement of Linear-Encoded Facial Semantics

Yutong Zheng, Yu-Kai Huang, Ran Tao +2

We propose a method to disentangle linear-encoded facial semantics from StyleGAN without external supervision. The method derives from linear regression and sparse representation l…

cs.CV202122 cited

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Chenchen Zhu, Fangyi Chen, Uzair Ahmed +2

Few-shot object detection is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data. Its performance is largely affected by the data s…

cs.CV20212 cited

Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning

Zhiqiang Shen, Zechun Liu, Jie Qin +2

The goal of few-shot learning is to learn a classifier that can recognize unseen classes from limited support data with labels. A common practice for this task is to train a model…

cs.CV2021

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration

Zhiqiang Shen, Zechun Liu, Jie Qin +3

Previous studies dominantly target at self-supervised learning on real-valued networks and have achieved many promising results. However, on the more challenging binary neural netw…