Mind the Gap: Disentangling Performance Bottlenecks in Video Instance Segmentation 事件

Mind the Gap: Disentangling Performance Bottlenecks in Video Instance Segmentation arXiv:2606.07394v1 Announce Type: new Abstract: In Video Instance Segmentation (VIS), classification, segmentation, and tracking objectives are jointly evaluated, but their individual contributions to performance loss remain opaque. We introduce a diagnostic framework that formulates identity and class assignment as an Integer Linear Program (ILP), yielding a model-agnostic oracle that hierarchically isolates eac