Timezone: »
Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous knowledge because the teacher is updated with the past student only. To alleviate this problem, we propose a novel self-training strategy, which allows the model to learn from the future. Concretely, at each training step, we first virtually optimize the student (i.e., caching the gradients without applying them to the model weights), then update the teacher with the virtual future student, and finally ask the teacher to produce pseudo-labels for the current student as the guidance. In this way, we manage to improve the quality of pseudo-labels and thus boost the performance. We also develop two variants of our future-self-training (FST) framework through peeping at the future both deeply (FST-D) and widely (FST-W). Taking the tasks of unsupervised domain adaptive semantic segmentation and semi-supervised semantic segmentation as the instances, we experimentally demonstrate the effectiveness and superiority of our approach under a wide range of settings. Code is available at https://github.com/usr922/FST.
Author Information
Ye Du (Beijing University of Aeronautics and Astronautics)
Yujun Shen (Ant Research)
Haochen Wang (Institute of automation, Chinese Academy of Sciences)
Jingjing Fei (SenseTime Research)
Wei Li (National Chiao Tung University)
Liwei Wu (SenseTime Research)
Rui Zhao (Qing Yuan Research Institute, Shanghai Jiao Tong University)
Zehua Fu (Hangzhou Innovation Institute, Beihang University)
Qingjie LIU (Beihang University)
More from the Same Authors
-
2022 Poster: Unsupervised Object Detection Pretraining with Joint Object Priors Generation and Detector Learning »
Yizhou Wang · Meilin Chen · SHIXIANG TANG · Feng Zhu · Haiyang Yang · LEI BAI · Rui Zhao · Yunfeng Yan · Donglian Qi · Wanli Ouyang -
2022 Poster: A Unified Model for Multi-class Anomaly Detection »
Zhiyuan You · Lei Cui · Yujun Shen · Kai Yang · Xin Lu · Yu Zheng · Xinyi Le -
2022 Poster: Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks »
Zhiyang Chen · Yousong Zhu · Zhaowen Li · Fan Yang · Wei Li · Haixin Wang · Chaoyang Zhao · Liwei Wu · Rui Zhao · Jinqiao Wang · Ming Tang -
2022 Spotlight: Lightning Talks 5A-4 »
Yangrui Chen · Zhiyang Chen · Liang Zhang · Hanqing Wang · Jiaqi Han · Shuchen Wu · shaohui peng · Ganqu Cui · Yoav Kolumbus · Noemi Elteto · Xing Hu · Anwen Hu · Wei Liang · Cong Xie · Lifan Yuan · Noam Nisan · Wenbing Huang · Yousong Zhu · Ishita Dasgupta · Luc V Gool · Tingyang Xu · Rui Zhang · Qin Jin · Zhaowen Li · Meng Ma · Bingxiang He · Yangyi Chen · Juncheng Gu · Wenguan Wang · Ke Tang · Yu Rong · Eric Schulz · Fan Yang · Wei Li · Zhiyuan Liu · Jiaming Guo · Yanghua Peng · Haibin Lin · Haixin Wang · Qi Yi · Maosong Sun · Ruizhi Chen · Chuan Wu · Chaoyang Zhao · Yibo Zhu · Liwei Wu · xishan zhang · Zidong Du · Rui Zhao · Jinqiao Wang · Ling Li · Qi Guo · Ming Tang · Yunji Chen -
2022 Spotlight: Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator »
Zifan Shi · Yinghao Xu · Yujun Shen · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Spotlight: Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks »
Zhiyang Chen · Yousong Zhu · Zhaowen Li · Fan Yang · Wei Li · Haixin Wang · Chaoyang Zhao · Liwei Wu · Rui Zhao · Jinqiao Wang · Ming Tang -
2022 Spotlight: Lightning Talks 5B-1 »
Devansh Arpit · Xiaojun Xu · Zifan Shi · Ivan Skorokhodov · Shayan Shekarforoush · Zhan Tong · Yiqun Wang · Shichong Peng · Linyi Li · Ivan Skorokhodov · Huan Wang · Yibing Song · David Lindell · Yinghao Xu · Seyed Alireza Moazenipourasil · Sergey Tulyakov · Peter Wonka · Yiqun Wang · Ke Li · David Fleet · Yujun Shen · Yingbo Zhou · Bo Li · Jue Wang · Peter Wonka · Marcus Brubaker · Caiming Xiong · Limin Wang · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Spotlight: Lightning Talks 3B-3 »
Sitao Luan · Zhiyuan You · Ruofan Liu · Linhao Qu · Yuwei Fu · Jiaxi Wang · Chunyu Wei · Jian Liang · xiaoyuan luo · Di Wu · Yun Lin · Lei Cui · Ji Wu · Chenqing Hua · Yujun Shen · Qincheng Lu · XIANGLIN YANG · Benoit Boulet · Manning Wang · Di Liu · Lei Huang · Fei Wang · Kai Yang · Jiaqi Zhu · Jin Song Dong · Zhijian Song · Xin Lu · Mingde Zhao · Shuyuan Zhang · Yu Zheng · Xiao-Wen Chang · Xinyi Le · Doina Precup -
2022 Spotlight: A Unified Model for Multi-class Anomaly Detection »
Zhiyuan You · Lei Cui · Yujun Shen · Kai Yang · Xin Lu · Yu Zheng · Xinyi Le -
2022 Poster: Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator »
Zifan Shi · Yinghao Xu · Yujun Shen · Deli Zhao · Qifeng Chen · Dit-Yan Yeung -
2022 Poster: Improving GANs with A Dynamic Discriminator »
Ceyuan Yang · Yujun Shen · Yinghao Xu · Deli Zhao · Bo Dai · Bolei Zhou -
2021 Poster: MST: Masked Self-Supervised Transformer for Visual Representation »
Zhaowen Li · Zhiyang Chen · Fan Yang · Wei Li · Yousong Zhu · Chaoyang Zhao · Rui Deng · Liwei Wu · Rui Zhao · Ming Tang · Jinqiao Wang