# ISDA: Position-Aware Instance Segmentation with Deformable Attention Source: [ISDA: Position-Aware Instance Segmentation with Deformable Attention]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:38:09.398Z Authors: Kaining Ying, Zhenhua Wang, Cong Bai, Pengfei Zhou Published: 2022-02-23T12:30:18.000Z ## Abstract Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing. Here we propose a novel end-to-end instance segmentation method termed ISDA. It reshapes the task into predicting a set of object masks, which are generated via traditional convolution operation with learned position-aware kernels and features of objects. Such kernels and features are learned by leveraging a deformable attention network with multi-scale representation. Thanks to the introduced set-prediction mechanism, the proposed method is NMS-free. Empirically, ISDA outperforms Mask R-CNN (the strong baseline) by 2.6 points on MS-COCO, and achieves leading performance compared with recent models. Code will be available soon. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Instance Segmentation on COCO 2017 (test-dev)](): Instance Segmentation; COCO 2017 (test-dev); AP (Overall): 38.7. ## Original sources and implementation [Original paper]() [PDF]()