mlsanityData to 7 Oct 2026

What makes for effective detection proposals?

arXiv 1502.05082 ↗First posted 17 Feb 2015cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 11; 2023: 5; 2024: 7; 2025: 4; 2026: 1.

38 papers.

Sort:

By area:

  1. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  2. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  3. 2023FACET: Fairness in Computer Vision Evaluation Benchmarkcited by 58
  4. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  5. 2023Instance Neural Radiance Fieldcited by 39
  6. 2021A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detectioncited by 31
  7. 2022How stable are Transferability Metrics evaluations?cited by 30
  8. 2022Robust Double-Encoder Network for RGB-D Panoptic Segmentationcited by 8
  9. 2022Scaling Novel Object Detection with Weakly Supervised Detection Transformerscited by 7
  10. 2022Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sectionscited by 7
  11. 2023Oriented object detection in optical remote sensing images using deep learning: a surveycited by 7
  12. 2024Meta-Point Learning and Refining for Category-Agnostic Pose Estimationcited by 7
26 more
  1. 2021Postdisaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networkscited by 6
  2. 2024RETR: Multi-View Radar Detection Transformer for Indoor Perceptioncited by 6
  3. 2021Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detectioncited by 5
  4. 2022Localizing Small Apples in Complex Apple Orchard Environmentscited by 5
  5. 2021Superpixel-based Refinement for Object Proposal Generationcited by 4
  6. 2021Diagnosing Errors in Video Relation Detectorscited by 4
  7. 2021DeepFH Segmentations for Superpixel-based Object Proposal Refinementcited by 3
  8. 2022Tunable Hybrid Proposal Networks for the Open Worldcited by 2
  9. 2023LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detectioncited by 2
  10. 2021Finding Deviated Behaviors of the Compressed DNN Models for Image Classificationscited by 1
  11. 2024FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentationcited by 1
  12. 2024Weakly Supervised Panoptic Segmentation for Defect-Based Grading of Fresh Producecited by 1
  13. 2025Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervisioncited by 1
  14. 2025REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusioncited by 1
  15. 2022Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMaskcited by 0
  16. 2022Learning High-quality Proposals for Acne Detectioncited by 0
  17. 2022N-RPN: Hard Example Learning for Region Proposal Networkscited by 0
  18. 2022Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videoscited by 0
  19. 2022Semi-supervised object detection based on single-stage detector for thighbone fracture localizationcited by 0
  20. 2023Progression-Guided Temporal Action Detection in Videoscited by 0
  21. 2024Aligning Object Detector Bounding Boxes with Human Preferencecited by 0
  22. 2024Improving Detection of Person Class Using Dense Poolingcited by 0
  23. 2024Edge Weight Prediction For Category-Agnostic Pose Estimationcited by 0
  24. 2025Topological Structure Description for Artcode Detection Using the Shape of Orientation Histogramcited by 0
  25. 2025Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encodingcited by 0
  26. 2026Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabularycited by 0