mlsanityData to 7 Oct 2026

Zero-shot Object Counting with Good Exemplars

arXiv 2407.04948 ↗First posted 6 Jul 2024cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a critical challenge in current ZOC methods lies in their inability to identify high-quality exemplars effectively. This deficiency hampers scalability across diverse classes and undermines the development of strong visual associations between the identified classes and image content. To this end, we propose the Visual Association-based Zero-shot Object Counting (VA-Count) framework. VA-Count consists of an Exemplar Enhancement Module (EEM) and a Noise Suppression Module (NSM) that synergistically refine the process of class exemplar identification while minimizing the consequences of incorrect object identification. The EEM utilizes advanced vision-language pretaining models to discover potential exemplars, ensuring the framework's adaptability to various classes. Meanwhile, the NSM employs contrastive learning to differentiate between optimal and suboptimal exemplar pairs, reducing the negative effects of erroneous exemplars. VA-Count demonstrates its effectiveness and scalability in zero-shot contexts with superior performance on two object counting datasets.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 39 of its 51 references that are in the map. First posted on arXiv 6 Jul 2024.

Builds on

39 of 51 references.

References · 39

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Segment Anythingcited by 8,158
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  6. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  7. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  8. 2018Zero-Shot Object Detectioncited by 189
  9. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 177
  10. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 155
  11. 2021Learning To Count Everythingcited by 149
  12. 2022Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbonecited by 109
27 more
  1. 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
  2. 2018Class-Agnostic Countingcited by 85
  3. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 82
  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. 2022A Low-Shot Object Counting Network With Iterative Prototype Adaptationcited by 65
  7. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  8. 2023Zero-shot Object Countingcited by 57
  9. 2022Few-shot Object Counting and Detectioncited by 55
  10. 2023RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Searchcited by 53
  11. 2018Iterative Crowd Countingcited by 48
  12. 2023VLCounter: Text-aware Visual Representation for Zero-Shot Object Countingcited by 45
  13. 2022Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervisioncited by 41
  14. 2021Zero-Shot Instance Segmentationcited by 40
  15. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  16. 2023Training-free Object Counting with Promptscited by 34
  17. 2022Exemplar Free Class Agnostic Countingcited by 32
  18. 2020Adaptive Mixture Regression Network with Local Counting Map for Crowd Countingcited by 28
  19. 2023Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Countingcited by 25
  20. 2020Completely Self-Supervised Crowd Counting via Distribution Matchingcited by 22
  21. 2023Region Generation and Assessment Network for Occluded Person Re-Identificationcited by 20
  22. 2022Vision-Language Pre-Training for Boosting Scene Text Detectorscited by 18
  23. 2023DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Countingcited by 18
  24. 2023DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Countingcited by 12
  25. 2023RGB-D Indiscernible Object Counting in Underwater Scenescited by 9
  26. 2022Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Countingcited by 5
  27. 2021Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 7.

21 papers.

Sort:

By area:

  1. 2025DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Responsecited by 35
  2. 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Countingcited by 19
  3. 2025YOLO-Count: Differentiable Object Counting for Text-to-Image Generationcited by 10
  4. 2025A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approachescited by 7
  5. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluationcited by 7
  6. 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matchingcited by 6
  7. 2025Instruct2See: Learning to Remove Any Obstructions Across Distributionscited by 3
  8. 2025FiGO: Fine-Grained Object Counting without Annotationscited by 2
  9. 2025Text-promptable Object Counting via Quantity Awareness Enhancementcited by 2
  10. 2026Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Countingcited by 2
  11. 2025Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localizationcited by 1
  12. 2025Expanding Zero-Shot Object Counting with Rich Promptscited by 1
9 more
  1. 2025Object Counting with GPT-4o and GPT-5: A Comparative Studycited by 1
  2. 2026CountEx: Fine-Grained Counting via Exemplars and Exclusioncited by 1
  3. 2026AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Countingcited by 1
  4. 2025FocalCount: Towards Class-Count Imbalance in Class-Agnostic Countingcited by 0
  5. 2025CountZES: Counting via Zero-Shot Exemplar Selectioncited by 0
  6. 2026Count Anythingcited by 0
  7. 2026RT-Counter: Real-Time Text-Guided Open-Vocabulary Object Countingcited by 0
  8. 2026RECOUNT: Reference-guided Counting with Synthetic Visual Exemplarscited by 0
  9. 2026DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Countingcited by 0