Distilling Virtual Examples for Long-Tailed Recognition

Yin-Yin He, Jianxin Wu, Xiu-Shen Wei; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 235-244


We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treating the predictions of a teacher model as virtual exam- ples, we prove that distilling from these virtual examples is equivalent to label distribution learning under certain con- straints. We show that when the virtual example distribu- tion becomes flatter than the original input distribution, the under-represented tail classes will receive significant im- provements, which is crucial in long-tailed recognition. The proposed DiVE method can explicitly tune the virtual exam- ple distribution to become flat. Extensive experiments on three benchmark datasets, including the large-scale iNat- uralist ones, justify that the proposed DiVE method can significantly outperform state-of-the-art methods. Further- more, additional analyses and experiments verify the virtual example interpretation, and demonstrate the effectiveness of tailored designs in DiVE for long-tailed problems.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{He_2021_ICCV, author = {He, Yin-Yin and Wu, Jianxin and Wei, Xiu-Shen}, title = {Distilling Virtual Examples for Long-Tailed Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {235-244} }