Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

Hao Li, Chenxin Tao, Xizhou Zhu, Xiaogang Wang, Gao Huang, Jifeng Dai

Keywords: Loss Function Search, Metric Surrogate, Semantic Segmentation

Abstract: Designing proper loss functions is essential in training deep networks. Especially in the field of semantic segmentation, various evaluation metrics have been proposed for diverse scenarios. Despite the success of the widely adopted cross-entropy loss and its variants, the mis-alignment between the loss functions and evaluation metrics degrades the network performance. Meanwhile, manually designing loss functions for each specific metric requires expertise and significant manpower. In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric. We substitute the non-differentiable operations in the metrics with parameterized functions, and conduct parameter search to optimize the shape of loss surfaces. Two constraints are introduced to regularize the search space and make the search efficient. Extensive experiments on PASCAL VOC and Cityscapes demonstrate that the searched surrogate losses outperform the manually designed loss functions consistently. The searched losses can generalize well to other datasets and networks. Code shall be released at https://github.com/fundamentalvision/Auto-Seg-Loss.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Auto Seg-Loss is the first general framework for searching surrogate losses for mainstream semantic segmentation metrics.

Data: [Cityscapes](https://paperswithcode.com/dataset/cityscapes)