BZBo Zhao

Bo Zhao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bo Zhao has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Image Captions are Natural Prompts for Training Data Synthesis

    by Shiye Lei, Hao Chen, Sen Zhang, Bo Zhao, Dacheng Tao


  • Open Access

    Normalizing Batch Normalization for Long-Tailed Recognition

    by Yuxiang Bao, Guoliang Kang, Linlin Yang, Xiaoyue Duan, Bo Zhao, Baochang Zhang

    In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent class. Most previous works attempt to rectify the network bias from the data-level or from the classifier-level. Differently, in this paper, we identify that the bias towards the frequent class may be encoded into features, i.e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features. Based on such an observation, we introduce a simple yet effective approach, normalizing the parameters of Batch Normalization (BN) layer to explicitly rectify the feature bias. To achieve this end, we represent the Weight/Bias parameters of a BN layer as a vector, normalize it into a unit one and multiply the unit vector by a scalar learnable parameter. Through decoupling the direction and magnitude of parameters in BN layer to learn, the Weight/Bias exhibits a more balanced distribution and thus the strength of features becomes more even. Extensive experiments on various long-tailed recognition benchmarks (i.e., CIFAR-10/100-LT, ImageNet-LT and iNaturalist 2018) show that our method outperforms previous state-of-the-arts remarkably. The code and checkpoints are available at https://github.com/yuxiangbao/NBN.

  • Normalizing Batch Normalization for Long-Tailed Recognition

    by Yuxiang Bao, Guoliang Kang, Linlin Yang, Xiaoyue Duan, Bo Zhao, Baochang Zhang

    In real-world scenarios, the number of training samples across classes usually subjects to a long-tailed distribution. The conventionally trained network may achieve unexpected inferior performance on the rare class compared to the frequent class. Most previous works attempt to rectify the network bias from the data-level or from the classifier-level. Differently, in this paper, we identify that the bias towards the frequent class may be encoded into features, i.e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features. Based on such an observation, we introduce a simple yet effective approach, normalizing the parameters of Batch Normalization (BN) layer to explicitly rectify the feature bias. To achieve this end, we represent theWeight/Bias parameters of a BN layer as a vector, normalize it into a unit one and multiply the unit vector by a scalar learnable parameter. Through decoupling the direction and magnitude of parameters in BN layer to learn, the Weight/Bias exhibits a more balanced distribution and thus the strength of features becomes more even. Extensive experiments on various long-tailed recognition benchmarks (i.e., CIFAR-10/100-LT, ImageNet-LT and iNaturalist 2018) show that our method outperforms previous state-of-the-arts remarkably.


  • Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking

    by Jiyao Zhang, Weiyao Huang, Bo Peng, Mingdong Wu, Fei Hu, Zijian Chen, Bo Zhao, Hao Dong