Long-tailed class distributions are prevalent among the practical applications of object detection and instance segmentation. Prior work in long-tail instance segmentation addresses the imbalance of losses between rare and frequent categories by reducing the penalty for a model incorrectly predicting a rare class label. We demonstrate that the rare categories are heavily suppressed by correct background predictions, which reduces the probability for all foreground categories with equal weight. Due to the relative infrequency of rare categories, this leads to an imbalance that biases towards predicting more frequent categories. Based on this insight, we develop DropLoss -- a novel adaptive loss to compensate for this imbalance without a trade-off between rare and frequent categories. With this loss, we show state-of-the-art mAP across rare, common, and frequent categories on the LVIS dataset.


If you find this project useful, please cite this work:


  author 	= {Ting-I Hsieh and Esther Robb and Hwann-Tzong Chen and Jia-Bin Huang},
  title     = {DropLoss for Long-Tail Instance Segmentation},
  booktitle = {Proceedings of the Workshop on Artificial Intelligence Safety 2021
               (SafeAI 2021) co-located with the Thirty-Fifth {AAAI} Conference on
               Artificial Intelligence {(AAAI} 2021), Virtual, February 8, 2021},
  year      = {2021}