Timezone: »
Learning with noisy labels is a practically challenging problem in weakly supervised learning. In the existing literature, open-set noises are always considered to be poisonous for generalization, similar to closed-set noises. In this paper, we empirically show that open-set noisy labels can be non-toxic and even benefit the robustness against inherent noisy labels. Inspired by the observations, we propose a simple yet effective regularization by introducing Open-set samples with Dynamic Noisy Labels (ODNL) into training. With ODNL, the extra capacity of the neural network can be largely consumed in a way that does not interfere with learning patterns from clean data. Through the lens of SGD noise, we show that the noises induced by our method are random-direction, conflict-free and biased, which may help the model converge to a flat minimum with superior stability and enforce the model to produce conservative predictions on Out-of-Distribution instances. Extensive experimental results on benchmark datasets with various types of noisy labels demonstrate that the proposed method not only enhances the performance of many existing robust algorithms but also achieves significant improvement on Out-of-Distribution detection tasks even in the label noise setting.
Author Information
Hongxin Wei (Nanyang Technological University)
Lue Tao (Nanjing University of Aeronautics and Astronautics)
RENCHUNZI XIE (Nanyang Technological University)
Bo An (Nanyang Technological University)
More from the Same Authors
-
2022 Poster: Can Adversarial Training Be Manipulated By Non-Robust Features? »
Lue Tao · Lei Feng · Hongxin Wei · Jinfeng Yi · Sheng-Jun Huang · Songcan Chen -
2022 Poster: Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses »
Yuzhou Cao · Tianchi Cai · Lei Feng · Lihong Gu · Jinjie GU · Bo An · Gang Niu · Masashi Sugiyama -
2022 Poster: ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection »
HUIPING ZHUANG · Zhenyu Weng · Hongxin Wei · RENCHUNZI XIE · Kar-Ann Toh · Zhiping Lin -
2023 Poster: Offline RL with Discrete Proxy Representations for Generalizability in POMDPs »
Pengjie Gu · Xinyu Cai · Dong Xing · Xinrun Wang · Mengchen Zhao · Bo An -
2023 Poster: Regression with Cost-based Rejection »
Xin Cheng · Yuzhou Cao · Haobo Wang · Hongxin Wei · Bo An · Lei Feng -
2023 Poster: Computing Optimal Nash Equilibria in Multiplayer Games »
Youzhi Zhang · Bo An · Venkatramanan Subrahmanian -
2023 Poster: In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer »
Yuzhou Cao · Hussein Mozannar · Lei Feng · Hongxin Wei · Bo An -
2023 Poster: Few-shot Generation via Recalling the Episodic-Semantic Memory like Human Being »
Zhibin Duan · Zhiyi Lv · Chaojie Wang · Bo Chen · Bo An · Mingyuan Zhou -
2023 Poster: State Regularized Policy Optimization on Data with Dynamics Shift »
Zhenghai Xue · Qingpeng Cai · Shuchang Liu · Dong Zheng · Peng Jiang · Kun Gai · Bo An -
2023 Poster: On the Importance of Feature Separability in Predicting Out-Of-Distribution Error »
RENCHUNZI XIE · Hongxin Wei · Lei Feng · Yuzhou Cao · Bo An -
2023 Poster: TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning »
Shuo Sun · Molei Qin · Wentao Zhang · Haochong Xia · Chuqiao Zong · Jie Ying · Yonggang Xie · Lingxuan Zhao · Xinrun Wang · Bo An -
2022 Spotlight: Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems »
Yanchen Deng · Shufeng Kong · Caihua Liu · Bo An -
2022 Spotlight: Lightning Talks 6A-1 »
Ziyi Wang · Nian Liu · Yaming Yang · Qilong Wang · Yuanxin Liu · Zongxin Yang · Yizhao Gao · Yanchen Deng · Dongze Lian · Nanyi Fei · Ziyu Guan · Xiao Wang · Shufeng Kong · Xumin Yu · Daquan Zhou · Yi Yang · Fandong Meng · Mingze Gao · Caihua Liu · Yongming Rao · Zheng Lin · Haoyu Lu · Zhe Wang · Jiashi Feng · Zhaolin Zhang · Deyu Bo · Xinchao Wang · Chuan Shi · Jiangnan Li · Jiangtao Xie · Jie Zhou · Zhiwu Lu · Wei Zhao · Bo An · Jiwen Lu · Peihua Li · Jian Pei · Hao Jiang · Cai Xu · Peng Fu · Qinghua Hu · Yijie Li · Weigang Lu · Yanan Cao · Jianbin Huang · Weiping Wang · Zhao Cao · Jie Zhou -
2022 Spotlight: Lightning Talks 2A-2 »
Harikrishnan N B · Jianhao Ding · Juha Harviainen · Yizhen Wang · Lue Tao · Oren Mangoubi · Tong Bu · Nisheeth Vishnoi · Mohannad Alhanahnah · Mikko Koivisto · Aditi Kathpalia · Lei Feng · Nithin Nagaraj · Hongxin Wei · Xiaozhu Meng · Petteri Kaski · Zhaofei Yu · Tiejun Huang · Ke Wang · Jinfeng Yi · Jian Liu · Sheng-Jun Huang · Mihai Christodorescu · Songcan Chen · Somesh Jha -
2022 Spotlight: Can Adversarial Training Be Manipulated By Non-Robust Features? »
Lue Tao · Lei Feng · Hongxin Wei · Jinfeng Yi · Sheng-Jun Huang · Songcan Chen -
2022 Poster: Alleviating "Posterior Collapse'' in Deep Topic Models via Policy Gradient »
Yewen Li · Chaojie Wang · Zhibin Duan · Dongsheng Wang · Bo Chen · Bo An · Mingyuan Zhou -
2022 Poster: Deep Attentive Belief Propagation: Integrating Reasoning and Learning for Solving Constraint Optimization Problems »
Yanchen Deng · Shufeng Kong · Caihua Liu · Bo An -
2022 Poster: Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE »
Yewen Li · Chaojie Wang · Xiaobo Xia · Tongliang Liu · xin miao · Bo An -
2021 Poster: RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents »
Wei Qiu · Xinrun Wang · Runsheng Yu · Rundong Wang · Xu He · Bo An · Svetlana Obraztsova · Zinovi Rabinovich -
2021 Poster: Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training »
Lue Tao · Lei Feng · Jinfeng Yi · Sheng-Jun Huang · Songcan Chen -
2019 Poster: Manipulating a Learning Defender and Ways to Counteract »
Jiarui Gan · Qingyu Guo · Long Tran-Thanh · Bo An · Michael Wooldridge