mlsanityData to 7 Oct 2026

Evaluating Context for Deep Object Detectors

arXiv 2205.02887 ↗First posted 5 May 2022cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Which object detector is suitable for your context sensitive task? Deep object detectors exploit scene context for recognition differently. In this paper, we group object detectors into 3 categories in terms of context use: no context by cropping the input (RCNN), partial context by cropping the featuremap (two-stage methods) and full context without any cropping (single-stage methods). We systematically evaluate the effect of context for each deep detector category. We create a fully controlled dataset for varying context and investigate the context for deep detectors. We also evaluate gradually removing the background context and the foreground object on MS COCO. We demonstrate that single-stage and two-stage object detectors can and will use the context by virtue of their large receptive field. Thus, choosing the best object detector may depend on the application context.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 29 references that are in the map. First posted on arXiv 5 May 2022.

Builds on

26 of 29 references.

References · 26

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2018YOLOv3: An Incremental Improvementcited by 2,652
  9. 2017Deformable Convolutional Networkscited by 1,481
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  12. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 141
14 more
  1. 2020Don't Judge an Object by Its Context: Learning to Overcome Contextual Biascited by 91
  2. 2015Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networkscited by 80
  3. 2015Object detection via a multi-region & semantic segmentation-aware CNN modelcited by 47
  4. 2019Bag of Freebies for Training Object Detection Neural Networkscited by 47
  5. 2018Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationshipscited by 41
  6. 2019Putting visual object recognition in contextcited by 33
  7. 2019Small Object Detection using Context and Attentioncited by 21
  8. 2017CoupleNet: Coupling Global Structure with Local Parts for Object Detectioncited by 16
  9. 2021Hallucination In Object Detection -- A Study In Visual Part Verificationcited by 16
  10. 2020Shift Equivariance in Object Detectioncited by 13
  11. 2017Seeing What Is Not There: Learning Context to Determine Where Objects Are Missingcited by 11
  12. 2017Exploring the Bounds of the Utility of Context for Object Detectioncited by 10
  13. 2015Exploring Person Context and Local Scene Context for Object Detectioncited by 2
  14. 2018Object Detection with Mask-based Feature Encodingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2022Humans disagree with the IoU for measuring object detector localization errorcited by 4
  2. 2023VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 4
  3. 2022Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentationcited by 0
  4. 2024VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 0