mlsanityData to 7 Oct 2026

Zero-shot Object Counting

arXiv 2303.02001 ↗First posted 3 Mar 2023cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often unavailable for novel categories, especially for autonomous systems. Thus, we propose zero-shot object counting (ZSC), a new setting where only the class name is available during test time. Such a counting system does not require human annotators in the loop and can operate automatically. Starting from a class name, we propose a method that can accurately identify the optimal patches which can then be used as counting exemplars. Specifically, we first construct a class prototype to select the patches that are likely to contain the objects of interest, namely class-relevant patches. Furthermore, we introduce a model that can quantitatively measure how suitable an arbitrary patch is as a counting exemplar. By applying this model to all the candidate patches, we can select the most suitable patches as exemplars for counting. Experimental results on a recent class-agnostic counting dataset, FSC-147, validate the effectiveness of our method. Code is available at https://github.com/cvlab-stonybrook/zero-shot-counting

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 40 of its 58 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

40 of 58 references.

References · 40

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2017Wasserstein GANcited by 635
  3. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  4. 2018Zero-Shot Object Detectioncited by 189
  5. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  6. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  7. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 155
  8. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  9. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  10. 2018Context-Aware Crowd Countingcited by 150
  11. 2021Learning To Count Everythingcited by 149
  12. 2020Distribution Matching for Crowd Countingcited by 143
28 more
  1. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  2. 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
  3. 2018Class-Agnostic Countingcited by 85
  4. 2022Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Countingcited by 80
  5. 2022CounTR: Transformer-based Generalised Visual Countingcited by 79
  6. 2020Localization in the Crowd with Topological Constraintscited by 68
  7. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  8. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  9. 2020From Shadow Segmentation to Shadow Removalcited by 59
  10. 2022Few-shot Object Counting and Detectioncited by 55
  11. 2018Where are the Blobs: Counting by Localization with Point Supervisioncited by 54
  12. 2021Zero-Shot Instance Segmentationcited by 40
  13. 2014Zero Shot Recognition with Unreliable Attributescited by 39
  14. 2017A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuationcited by 39
  15. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  16. 2020Physics-based Shadow Image Decomposition for Shadow Removalcited by 38
  17. 2019Object Counting and Instance Segmentation with Image-level Supervisioncited by 35
  18. 2016Counting Everyday Objects in Everyday Scenescited by 34
  19. 2019Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Methodcited by 32
  20. 2022Exemplar Free Class Agnostic Countingcited by 32
  21. 2020Variational Feature Disentangling for Fine-Grained Few-Shot Classificationcited by 26
  22. 2021Leveraging Self-Supervision for Cross-Domain Crowd Countingcited by 24
  23. 2020Completely Self-Supervised Crowd Counting via Distribution Matchingcited by 22
  24. 2020Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Reviewcited by 20
  25. 2022Discrete-Constrained Regression for Local Counting Modelscited by 19
  26. 2016Co-localization with Category-Consistent Features and Geodesic Distance Propagationcited by 14
  27. 2019Weakly Labeling the Antarctic: The Penguin Colony Casecited by 12
  28. 2019Towards Partial Supervision for Generic Object Counting in Natural Scenescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 15; 2025: 20; 2026: 15.

57 papers.

Sort:

By area:

  1. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 82
  2. 2024CountGD: Multi-Modal Open-World Countingcited by 59
  3. 2024DAVE -- A Detect-and-Verify Paradigm for Low-Shot Countingcited by 49
  4. 2024AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?cited by 46
  5. 2023Open-world Text-specified Object Countingcited by 41
  6. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  7. 2023Training-free Object Counting with Promptscited by 34
  8. 2023Counting Guidance for High Fidelity Text-to-Image Synthesiscited by 24
  9. 2024Zero-shot Object Counting with Good Exemplarscited by 21
  10. 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Countingcited by 19
  11. 2024OmniCount: Multi-label Object Counting with Semantic-Geometric Priorscited by 16
  12. 2023ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Countingcited by 13
38 more
  1. 2024Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Countingcited by 11
  2. 2024OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videoscited by 10
  3. 2025Exploring Contextual Attribute Density in Referring Expression Countingcited by 10
  4. 2025YOLO-Count: Differentiable Object Counting for Text-to-Image Generationcited by 10
  5. 2023Zero-Shot Object Counting with Language-Vision Modelscited by 9
  6. 2024Every Shot Counts: Using Exemplars for Repetition Counting in Videoscited by 8
  7. 2024Assessing Sample Quality via the Latent Space of Generative Modelscited by 8
  8. 2024Counting Stacked Objectscited by 8
  9. 2025CountGD++: Generalized Prompting for Open-World Countingcited by 8
  10. 2025A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approachescited by 7
  11. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluationcited by 7
  12. 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matchingcited by 6
  13. 2025Point-to-Region Loss for Semi-Supervised Point-Based Crowd Countingcited by 6
  14. 2024Shadow Removal Refinement via Material-Consistent Shadow Edgescited by 5
  15. 2024TFCounter:Polishing Gems for Training-Free Object Countingcited by 2
  16. 2024Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentationcited by 2
  17. 2025FiGO: Fine-Grained Object Counting without Annotationscited by 2
  18. 2025SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Countingcited by 2
  19. 2025Text-promptable Object Counting via Quantity Awareness Enhancementcited by 2
  20. 2026Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Countingcited by 2
  21. 2024Enhancing Zero-shot Counting via Language-guided Exemplar Learningcited by 1
  22. 2025Expanding Zero-Shot Object Counting with Rich Promptscited by 1
  23. 2025Querying Autonomous Vehicle Point Clouds: Enhanced by 3D Object Counting with CounterNetcited by 1
  24. 2025Counting Through Occlusion: Framework for Open World Amodal Countingcited by 1
  25. 2025CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentationcited by 1
  26. 2025Object Counting with GPT-4o and GPT-5: A Comparative Studycited by 1
  27. 2026CountEx: Fine-Grained Counting via Exemplars and Exclusioncited by 1
  28. 2026Automated Counting of Stacked Objects in Industrial Inspectioncited by 1
  29. 2026Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Countingcited by 1
  30. 2026Count Anything at Any Granularitycited by 1
  31. 2026Unveiling the Visual Counting Bottleneck in Vision-Language Modelscited by 1
  32. 2026AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Countingcited by 1
  33. 2026Spatially-Aware Class-Agnostic Object Countingcited by 1
  34. 2024GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Countingcited by 0
  35. 2025FocalCount: Towards Class-Count Imbalance in Class-Agnostic Countingcited by 0
  36. 2025CountFormer: A Transformer Framework for Learning Visual Repetition and Structure in Class-Agnostic Object Countingcited by 0
  37. 2025Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoningcited by 0
  38. 2025CountZES: Counting via Zero-Shot Exemplar Selectioncited by 0

50 most cited of 57 All 57 (JSON)