mlsanityData to 7 Oct 2026

Zero-Shot Object Detection

arXiv 1804.04340 ↗First posted 12 Apr 2018cs.CVcited by 189

Not on the map. Why?

Abstract (arXiv)

We introduce and tackle the problem of zero-shot object detection (ZSD), which aims to detect object classes which are not observed during training. We work with a challenging set of object classes, not restricting ourselves to similar and/or fine-grained categories as in prior works on zero-shot classification. We present a principled approach by first adapting visual-semantic embeddings for ZSD. We then discuss the problems associated with selecting a background class and motivate two background-aware approaches for learning robust detectors. One of these models uses a fixed background class and the other is based on iterative latent assignments. We also outline the challenge associated with using a limited number of training classes and propose a solution based on dense sampling of the semantic label space using auxiliary data with a large number of categories. We propose novel splits of two standard detection datasets - MSCOCO and VisualGenome, and present extensive empirical results in both the traditional and generalized zero-shot settings to highlight the benefits of the proposed methods. We provide useful insights into the algorithm and conclude by posing some open questions to encourage further research.

Key facts. Cited by 189 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 40; 2022: 41; 2023: 57; 2024: 31; 2025: 14; 2026: 6.

189 papers.

Sort:

By area:

  1. 2021Grounded Language-Image Pre-trainingcited by 1,147
  2. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  3. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  4. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  5. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  6. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  7. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  8. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  9. 2022Open-Vocabulary DETR with Conditional Matchingcited by 220
  10. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  11. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  12. 2022F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Modelscited by 149
38 more
  1. 2022Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detectioncited by 145
  2. 2022PromptDet: Towards Open-vocabulary Detection using Uncurated Imagescited by 133
  3. 2023CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matchingcited by 133
  4. 2021OW-DETR: Open-world Detection Transformercited by 129
  5. 2021Simple multi-dataset detectioncited by 126
  6. 2023Aligning Bag of Regions for Open-Vocabulary Object Detectioncited by 119
  7. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  8. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  9. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  10. 2023Contextual Object Detection with Multimodal Large Language Modelscited by 100
  11. 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
  12. 2022Learning Object-Language Alignments for Open-Vocabulary Object Detectioncited by 95
  13. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
  14. 2023Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformerscited by 91
  15. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  16. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  17. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Modelscited by 72
  18. 2021Open Vocabulary Object Detection with Pseudo Bounding-Box Labelscited by 71
  19. 2022Fine-Grained Semantically Aligned Vision-Language Pre-Trainingcited by 68
  20. 2022Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillationcited by 67
  21. 2023Object-Aware Distillation Pyramid for Open-Vocabulary Object Detectioncited by 63
  22. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
  23. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  24. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 59
  25. 2023Zero-shot Object Countingcited by 57
  26. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  27. 2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
  28. 2021Opening up Open-World Trackingcited by 50
  29. 2021AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuningcited by 48
  30. 2024Better Call SAL: Towards Learning to Segment Anything in Lidarcited by 47
  31. 2023CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detectioncited by 46
  32. 2023Towards Open-Vocabulary Video Instance Segmentationcited by 45
  33. 2024DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLMcited by 45
  34. 2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
  35. 2023OvarNet: Towards Open-vocabulary Object Attribute Recognitioncited by 43
  36. 2021SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentationcited by 41
  37. 2022X-DETR: A Versatile Architecture for Instance-wise Vision-Language Taskscited by 41
  38. 2021Zero-Shot Instance Segmentationcited by 40

50 most cited of 189 All 189 (JSON)