SwInception -- Local Attention Meets Convolutions 事件

SwInception -- Local Attention Meets Convolutions arXiv:2605.29954v1 Announce Type: new Abstract: Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. Swin uses local attention to reduce complexity and yields excellent performance for many tasks but still tends to overfit on small datasets. To mitigate this weakness, we propose a novel architecture that further enhances Swin's inductive bias by int