BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation 事件

BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation arXiv:2511.19394v2 Announce Type: replace Abstract: Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data augmentation schemes; and collecting more labeled data. We take a different view, arguing that part of the problem lies in how the background is modeled. Common lesion segmentat