mlsanityData to 7 Oct 2026

Odd-One-Out: Anomaly Detection by Comparing with Neighbors

arXiv 2406.20099 ↗First posted 28 Jun 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel anomaly detection (AD) problem aimed at identifying `odd-looking' objects within a scene by comparing them to other objects present. Unlike traditional AD benchmarks with fixed anomaly criteria, our task detects anomalies specific to each scene by inferring a reference group of regular objects. To address occlusions, we use multiple views of each scene as input, construct 3D object-centric models for each instance from 2D views, enhancing these models with geometrically consistent part-aware representations. Anomalous objects are then detected through cross-instance comparison. We also introduce two new benchmarks, ToysAD-8K and PartsAD-15K as testbeds for future research in this task. We provide a comprehensive analysis of our method quantitatively and qualitatively on these benchmarks.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 42 of its 62 references that are in the map. First posted on arXiv 28 Jun 2024.

Builds on

42 of 62 references.

References · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023Segment Anythingcited by 8,158
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  11. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  12. 2020Center-based 3D Object Detection and Trackingcited by 1,143
30 more
  1. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  2. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  3. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  4. 2014Deep metric learning using Triplet networkcited by 421
  5. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  6. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  7. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  8. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  9. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  10. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  11. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  12. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  13. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  14. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  15. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  16. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  17. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  18. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  19. 2019The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentationcited by 122
  20. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  21. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  22. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 83
  23. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  24. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  25. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  26. 2019Detecting semantic anomaliescited by 50
  27. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  28. 2024Looking 3D: Anomaly Detection with 2D-3D Alignmentcited by 13
  29. 20233D Former: Monocular Scene Reconstruction with 3D SDF Transformerscited by 8
  30. 2023Low-shot Object Learning with Mutual Exclusivity Biascited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2026OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Modelscited by 4
  2. 2025Efficient Odd-One-Out Anomaly Detectioncited by 1
  3. 2026Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detectioncited by 0
  4. 2026MATCH: Flow Matching for Multi-View Anomaly Detectioncited by 0