mlsanityData to 7 Oct 2026

ISDA: Position-Aware Instance Segmentation with Deformable Attention

arXiv 2202.12251 ↗First posted 23 Feb 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 23 Feb 2022.

Builds on

27 of 34 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2017Mask R-CNNcited by 7,259
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  7. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  8. 2018Path Aggregation Network for Instance Segmentationcited by 796
  9. 2019VideoBERT: A Joint Model for Video and Language Representation Learningcited by 702
  10. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  11. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  12. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
15 more
  1. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  2. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  3. 2020Conditional Convolutions for Instance Segmentationcited by 314
  4. 2019SOLO: Segmenting Objects by Locationscited by 289
  5. 2019Mask Scoring R-CNNcited by 265
  6. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  7. 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 144
  8. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 122
  9. 2017Semantic Instance Segmentation with a Discriminative Loss Functioncited by 118
  10. 2019TensorMask: A Foundation for Dense Object Segmentationcited by 101
  11. 2020End-to-End Object Detection with Fully Convolutional Networkcited by 70
  12. 2021ISTR: End-to-End Instance Segmentation with Transformerscited by 52
  13. 2019An End-to-End Network for Panoptic Segmentationcited by 46
  14. 2015Recurrent Instance Segmentationcited by 21
  15. 2016Region-based semantic segmentation with end-to-end trainingcited by 9

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 2.

5 papers.

  1. 2023DVIS: Decoupled Video Instance Segmentation Frameworkcited by 77
  2. 2023CTVIS: Consistent Training for Online Video Instance Segmentationcited by 50
  3. 2025MOVE: Motion-Guided Few-Shot Video Object Segmentationcited by 6
  4. 2023Human-to-Human Interaction Detectioncited by 3
  5. 2025Segment Anything Across Shots: A Method and Benchmarkcited by 2