Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection
This addresses a domain-specific issue in SOD for researchers and practitioners by providing a more balanced evaluation framework, though it is incremental as it builds on existing metrics.
The paper tackles the problem of size-sensitive evaluation metrics in Salient Object Detection (SOD) for multi-object images, where larger objects dominate and smaller ones are ignored, by proposing a size-invariant approach that evaluates each object separately and combines results, leading to considerable improvements in detecting objects of different sizes.
This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://github.com/Ferry-Li/SI-SOD.