mlsanityData to 7 Oct 2026

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

arXiv 2006.02334 ↗First posted 3 Jun 2020cs.CVcited by 222

Not on the map. Why?

Abstract (arXiv)

Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone design for object detection. At the macro level, we propose Recursive Feature Pyramid, which incorporates extra feedback connections from Feature Pyramid Networks into the bottom-up backbone layers. At the micro level, we propose Switchable Atrous Convolution, which convolves the features with different atrous rates and gathers the results using switch functions. Combining them results in DetectoRS, which significantly improves the performances of object detection. On COCO test-dev, DetectoRS achieves state-of-the-art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation. The code is made publicly available.

Key facts. Cited by 222 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 57; 2022: 49; 2023: 59; 2024: 27; 2025: 18; 2026: 12.

222 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 199
  4. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  5. 2021Probabilistic two-stage detectioncited by 130
  6. 2021Simple multi-dataset detectioncited by 126
  7. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  8. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  9. 2022K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditionscited by 107
  10. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  11. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  12. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
38 more
  1. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  2. 2024OMG-Seg: Is One Model Good Enough For All Segmentation?cited by 73
  3. 2022Mitosis domain generalization in histopathology images -- The MIDOG challengecited by 66
  4. 2021Lite Vision Transformer with Enhanced Self-Attentioncited by 64
  5. 2022CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentationcited by 60
  6. 2021Part-aware Panoptic Segmentationcited by 56
  7. 2022Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkcited by 56
  8. 2022A Large-scale Multiple-objective Method for Black-box Attack against Object Detectioncited by 55
  9. 2021A Normalized Gaussian Wasserstein Distance for Tiny Object Detectioncited by 52
  10. 2022RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detectioncited by 51
  11. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  12. 2023Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detectioncited by 43
  13. 2022Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentationcited by 38
  14. 2021The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methodscited by 37
  15. 2021PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentationcited by 36
  16. 2023Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETRcited by 36
  17. 2021DISCO: accurate Discrete Scale Convolutionscited by 35
  18. 2022TubeFormer-DeepLab: Video Mask Transformercited by 35
  19. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  20. 2022Locality Guidance for Improving Vision Transformers on Tiny Datasetscited by 33
  21. 2021A Review on Deep Learning in UAV Remote Sensingcited by 32
  22. 2022From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instrumentscited by 32
  23. 2021FOVEA: Foveated Image Magnification for Autonomous Navigationcited by 31
  24. 2021PP-YOLOv2: A Practical Object Detectorcited by 30
  25. 2021Anchor DETR: Query Design for Transformer-Based Object Detectioncited by 30
  26. 2023DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Modelcited by 30
  27. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  28. 2024DQ-DETR: DETR with Dynamic Query for Tiny Object Detectioncited by 27
  29. 2024Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Datasetcited by 25
  30. 2021Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentationcited by 24
  31. 2024COCONut: Modernizing COCO Segmentationcited by 24
  32. 2022The 6th AI City Challengecited by 23
  33. 2021DeepLab2: A TensorFlow Library for Deep Labelingcited by 22
  34. 2023Object Detection with Transformers: A Reviewcited by 22
  35. 2023FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Visioncited by 22
  36. 2024HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detectioncited by 22
  37. 2021ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perceptioncited by 21
  38. 2023The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representationcited by 21

50 most cited of 222 All 222 (JSON)