Lijuan Huang1,2, Zhixian Liu3, Xinyu Zhou4, Jinping Liu4,*, Kunyi Zheng4, Yimei Yang2,4,*
CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.077655
- 08 May 2026
Abstract Many occluded and ambiguous ground truths exist in object detection, making detectors unable to obtain optimal training samples. In this article, we revisit the suboptimal sample issue in label assignment for object detection and propose a novel detector-agnostic strategy, termed FSS, to address it. FSS reformulates label assignment as the process of selecting high-quality sub-optimal samples and progressively transforming them into optimal ones. Specifically, for each candidate, we estimate the probability of being an optimal sample by jointly considering localization quality and classification confidence, thereby constructing an instance-wise probability matrix. Based on the spatial distribution More >