mlsanityData to 7 Oct 2026

Detecting Twenty-thousand Classes using Image-level Supervision

arXiv 2201.02605 ↗First posted 7 Jan 2022cs.CVcited by 613

Not on the map. Why?

Cited by 94 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Current object detectors are limited in vocabulary size due to the small scale of detection datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as their datasets are larger and easier to collect. We propose Detic, which simply trains the classifiers of a detector on image classification data and thus expands the vocabulary of detectors to tens of thousands of concepts. Unlike prior work, Detic does not need complex assignment schemes to assign image labels to boxes based on model predictions, making it much easier to implement and compatible with a range of detection architectures and backbones. Our results show that Detic yields excellent detectors even for classes without box annotations. It outperforms prior work on both open-vocabulary and long-tail detection benchmarks. Detic provides a gain of 2.4 mAP for all classes and 8.3 mAP for novel classes on the open-vocabulary LVIS benchmark. On the standard LVIS benchmark, Detic obtains 41.7 mAP when evaluated on all classes, or only rare classes, hence closing the gap in performance for object categories with few samples. For the first time, we train a detector with all the twenty-one-thousand classes of the ImageNet dataset and show that it generalizes to new datasets without finetuning. Code is available at urlhttps://github.com/facebookresearch/Detic.

Key facts. Cited by 613 papers in the map (data through 7 Oct 2026). Builds on 61 of its 81 references that are in the map. First posted on arXiv 7 Jan 2022.

Builds on

61 of 81 references.

References · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2017Mask R-CNNcited by 7,259
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  11. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
38 more
  1. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  2. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  3. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  4. 2021ImageNet-21K Pretraining for the Massescited by 607
  5. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  6. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
  7. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  8. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  9. 2016FastText.zip: Compressing text classification modelscited by 331
  10. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  11. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  12. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  13. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  14. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  15. 2018Zero-Shot Object Detectioncited by 189
  16. 2015Weakly Supervised Deep Detection Networkscited by 183
  17. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  18. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  19. 2021Probabilistic two-stage detectioncited by 130
  20. 2021Simple multi-dataset detectioncited by 126
  21. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  22. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  23. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  24. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  25. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  26. 2021Points as Queries: Weakly Semi-supervised Object Detection by Pointscited by 60
  27. 2019Dont Even Look Once: Synthesizing Features for Zero-Shot Detectioncited by 58
  28. 2021Evaluating Large-Vocabulary Object Detectors: The Devil is in the Detailscited by 57
  29. 2019Towards Segmenting Anything That Movescited by 51
  30. 2021Exploring Classification Equilibrium in Long-Tailed Object Detectioncited by 51
  31. 2020Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detectioncited by 50
  32. 2019Towards Precise End-to-end Weakly Supervised Object Detection Networkcited by 41
  33. 2020Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentationcited by 41
  34. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  35. 2021MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detectioncited by 33
  36. 2019Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detectioncited by 31
  37. 2020Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfercited by 28
  38. 2021Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detectioncited by 27

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 48; 2023: 192; 2024: 182; 2025: 114; 2026: 77.

613 papers.

Sort:

By area:

  1. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  2. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  3. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  4. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
  5. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  6. 2023LERF: Language Embedded Radiance Fieldscited by 538
  7. 2023Zero-shot Image-to-Image Translationcited by 503
  8. 2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 501
  9. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  10. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  11. 2023Scaling Open-Vocabulary Object Detectioncited by 335
  12. 2024Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Modelscited by 321
38 more
  1. 2023Training-Free Layout Control with Cross-Attention Guidancecited by 312
  2. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  3. 2023ConceptFusion: Open-set Multimodal 3D Mappingcited by 302
  4. 2023GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interestcited by 300
  5. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  6. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  7. 2022Open-Vocabulary DETR with Conditional Matchingcited by 220
  8. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  9. 2022Learning Video Representations from Large Language Modelscited by 204
  10. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  11. 2022Fine-tuned CLIP Models are Efficient Video Learnerscited by 178
  12. 2022ReCo: Region-Controlled Text-to-Image Generationcited by 177
  13. 2022PLA: Language-Driven Open-Vocabulary 3D Scene Understandingcited by 176
  14. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  15. 2022CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memorycited by 164
  16. 2023Alpha-CLIP: A CLIP Model Focusing on Wherever You Wantcited by 150
  17. 2022DETRs with Hybrid Matchingcited by 149
  18. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
  19. 2023PACO: Parts and Attributes of Common Objectscited by 146
  20. 2022Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detectioncited by 145
  21. 2022Unified Vision and Language Prompt Learningcited by 145
  22. 2023Structured World Models from Human Videoscited by 144
  23. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 135
  24. 2022PromptDet: Towards Open-vocabulary Detection using Uncurated Imagescited by 133
  25. 2023CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matchingcited by 133
  26. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  27. 2023Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidancecited by 123
  28. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 121
  29. 2022GRiT: A Generative Region-to-text Transformer for Object Understandingcited by 119
  30. 2024Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Modelscited by 118
  31. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trendscited by 117
  32. 2023CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Predictioncited by 114
  33. 2022Navigating to Objects in the Real Worldcited by 104
  34. 2023HomeRobot: Open-Vocabulary Mobile Manipulationcited by 104
  35. 2022VideoDex: Learning Dexterity from Internet Videoscited by 101
  36. 2023Contextual Object Detection with Multimodal Large Language Modelscited by 100
  37. 2022Learning Object-Language Alignments for Open-Vocabulary Object Detectioncited by 95
  38. 2024T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergycited by 94

50 most cited of 613 All 613 (JSON)