Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

arXiv:2302.05666v5 Announce Type: replace-cross
Abstract: Intersection over Union (IoU) losses are surrogates that directly optimize the Jaccard index. Leveraging IoU losses as part of the loss function have demonstrated superior performance in semantic segmentation tasks compared to optimizing pixel-wise losses such as the cross-entropy loss alone. However, we identify a lack of flexibility in these losses to support vital training techniques like label smoothing, knowledge distillation, and semi-supervised learning, mainly due to their inability to process soft labels. To address …

arxiv cs.ai cs.cv cs.lg index jaccard labels losses type