Auto Seg-Loss: Searching Metric Surrogates for 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.

References in corpus (7)

• Neural Architecture Search with Reinforcement Learning
• AutoML: A Survey of the State-of-the-Art
• DARTS: Differentiable Architecture Search
• Bridging Category-level and Instance-level Semantic Image Segmentation
• Training Deep Neural Networks via Direct Loss Minimization
• Loss Function Search for Face Recognition
• Segmentation Loss Odyssey

Cited by in corpus (4)

• Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression
• AutoLoss: Automated Loss Function Search in Recommendations
• HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning
• Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search