mlsanityData to 7 Oct 2026

Hallucination In Object Detection -- A Study In Visual Part Verification

arXiv 2106.02523 ↗First posted 4 Jun 2021cs.CV cs.AI cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

We show that object detectors can hallucinate and detect missing objects; potentially even accurately localized at their expected, but non-existing, position. This is particularly problematic for applications that rely on visual part verification: detecting if an object part is present or absent. We show how popular object detectors hallucinate objects in a visual part verification task and introduce the first visual part verification dataset: DelftBikes, which has 10,000 bike photographs, with 22 densely annotated parts per image, where some parts may be missing. We explicitly annotated an extra object state label for each part to reflect if a part is missing or intact. We propose to evaluate visual part verification by relying on recall and compare popular object detectors on DelftBikes.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

14 of 28 references.

References · 14

  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. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2018YOLOv3: An Incremental Improvementcited by 2,652
  6. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  7. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 141
  8. 2020Don't Judge an Object by Its Context: Learning to Overcome Contextual Biascited by 91
  9. 2015Object detection via a multi-region & semantic segmentation-aware CNN modelcited by 47
  10. 2018Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationshipscited by 41
  11. 2017CoupleNet: Coupling Global Structure with Local Parts for Object Detectioncited by 16
  12. 2020Shift Equivariance in Object Detectioncited by 13
2 more
  1. 2017Exploring the Bounds of the Utility of Context for Object Detectioncited by 10
  2. 2020Domain Adaptation with Joint Learning for Generic, Optical Car Part Recognition and Detection Systems (Go-CaRD)cited by 2

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 4; 2024: 3; 2025: 4.

16 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Modelscited by 80
  3. 2024GROUNDHOG: Grounding Large Language Models to Holistic Segmentationcited by 70
  4. 2025Treble Counterfactual VLMs: A Causal Approach to Hallucinationcited by 33
  5. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  6. 2022VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 8
  7. 2022Evaluating Context for Deep Object Detectorscited by 4
  8. 2022Humans disagree with the IoU for measuring object detector localization errorcited by 4
  9. 2023VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 4
  10. 2022'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTubecited by 3
  11. 2023Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identificationcited by 1
  12. 2023An Effective Two-stage Training Paradigm Detector for Small Datasetcited by 0
4 more
  1. 2024VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 0
  2. 2024Aligning Object Detector Bounding Boxes with Human Preferencecited by 0
  3. 2025Data-Efficient Challenges in Visual Inductive Priors: A Retrospectivecited by 0
  4. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0