Rethinking Evaluation of Infrared Small Target Detection

As an essential vision task, infrared small target detection (IRSTD)1 has seen significant advancements through deep learning. However, critical limitations in current evaluation protocols impede further progress. First, existing methods rely on fragmented pixel-and target-level specific metrics, which fails to provide a comprehensive view of model capabilities. Second, an excessive emphasis on overall performance scores obscures crucial error analysis, which is vital for identifying failure modes and improving real-world system performance. Third, the field predominantly adopts dataset-specific training-testing paradigms, hindering the understanding of model robustness and generalization across diverse infrared scenarios.