mlsanityData to 7 Oct 2026

Location-Sensitive Visual Recognition with Cross-IOU Loss

arXiv 2104.04899 ↗First posted 11 Apr 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks. This paper summarizes these tasks as location-sensitive visual recognition and proposes a unified solution named location-sensitive network (LSNet). Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object. The key to optimizing the LSNet lies in the ability of fitting various scales, for which we design a novel loss function named cross-IOU loss that computes the cross-IOU of each anchor point-landmark pair to approximate the global IOU between the prediction and ground-truth. The flexibly located and accurately predicted landmarks also enable LSNet to incorporate richer contextual information for visual recognition. Evaluated on the MS-COCO dataset, LSNet set the new state-of-the-art accuracy for anchor-free object detection (a 53.5% box AP) and instance segmentation (a 40.2% mask AP), and shows promising performance in detecting multi-scale human poses. Code is available at https://github.com/Duankaiwen/LSNet

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 58 of its 70 references that are in the map. First posted on arXiv 11 Apr 2021.

Builds on

58 of 70 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2015Fast R-CNNcited by 2,930
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
38 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2017Deformable Convolutional Networkscited by 1,481
  3. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  4. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  5. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  8. 2019Objects as Pointscited by 1,172
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  11. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  12. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  13. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  14. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  15. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  16. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  17. 2019YOLACT: Real-time Instance Segmentationcited by 441
  18. 2017Deep Layer Aggregationcited by 436
  19. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  20. 2016Convolutional Pose Machinescited by 325
  21. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  22. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  23. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  24. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  25. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  26. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  27. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  28. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  29. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  30. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  31. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  32. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  33. 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
  34. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  35. 2020Deep Snake for Real-Time Instance Segmentationcited by 111
  36. 2020Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detectioncited by 104
  37. 2019TensorMask: A Foundation for Dense Object Segmentationcited by 101
  38. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 6.

8 papers.

  1. 2021YOLOP: You Only Look Once for Panoptic Driving Perceptioncited by 82
  2. 2022E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentationcited by 27
  3. 2022YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perceptioncited by 25
  4. 2022BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extractioncited by 11
  5. 2022CenterNet++ for Object Detectioncited by 9
  6. 2022Unifying Visual Perception by Dispersible Points Learningcited by 3
  7. 2021Rethinking the Misalignment Problem in Dense Object Detectioncited by 1
  8. 2022Growing Instance Mask on Leafcited by 1