mlsanityData to 7 Oct 2026

A Low-Shot Object Counting Network With Iterative Prototype Adaptation

arXiv 2211.08217 ↗First posted 15 Nov 2022cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

We consider low-shot counting of arbitrary semantic categories in the image using only few annotated exemplars (few-shot) or no exemplars (no-shot). The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts. Existing methods extract queries by feature pooling which neglects the shape information (e.g., size and aspect) and leads to a reduced object localization accuracy and count estimates. We propose a Low-shot Object Counting network with iterative prototype Adaptation (LOCA). Our main contribution is the new object prototype extraction module, which iteratively fuses the exemplar shape and appearance information with image features. The module is easily adapted to zero-shot scenarios, enabling LOCA to cover the entire spectrum of low-shot counting problems. LOCA outperforms all recent state-of-the-art methods on FSC147 benchmark by 20-30% in RMSE on one-shot and few-shot and achieves state-of-the-art on zero-shot scenarios, while demonstrating better generalization capabilities.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

23 of 34 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2017Mask R-CNNcited by 7,259
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  10. 2017Focal Loss for Dense Object Detectioncited by 749
  11. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  12. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 155
11 more
  1. 2021Learning To Count Everythingcited by 149
  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. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  8. 2022Few-shot Object Counting and Detectioncited by 55
  9. 2022Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervisioncited by 41
  10. 2022Exemplar Free Class Agnostic Countingcited by 32
  11. 2021Object Counting: You Only Need to Look at Onecited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 16; 2025: 23; 2026: 18.

65 papers.

Sort:

By area:

  1. 2023LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmarkcited by 169
  2. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 82
  3. 2024CountGD: Multi-Modal Open-World Countingcited by 59
  4. 2024DAVE -- A Detect-and-Verify Paradigm for Low-Shot Countingcited by 49
  5. 2023Open-world Text-specified Object Countingcited by 41
  6. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  7. 2024Zero-shot Object Counting with Good Exemplarscited by 21
  8. 2024A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentationcited by 21
  9. 2023T-Rex: Counting by Visual Promptingcited by 20
  10. 2024LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Modelscited by 20
  11. 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Countingcited by 19
  12. 2025CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Rewardcited by 15
38 more
  1. 2023ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Countingcited by 13
  2. 2024Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Countingcited by 11
  3. 2025Open-World Object Counting in Videoscited by 11
  4. 2024OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videoscited by 10
  5. 2025Exploring Contextual Attribute Density in Referring Expression Countingcited by 10
  6. 2025CountGD++: Generalized Prompting for Open-World Countingcited by 8
  7. 2025A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approachescited by 7
  8. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluationcited by 7
  9. 2023Semantic Generative Augmentations for Few-Shot Countingcited by 6
  10. 2024Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wildcited by 6
  11. 2025CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbonescited by 6
  12. 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matchingcited by 6
  13. 2023Learning to Count without Annotationscited by 5
  14. 2024Learning Spatial Similarity Distribution for Few-shot Object Countingcited by 5
  15. 2025Generalized-Scale Object Counting with Gradual Query Aggregationcited by 5
  16. 2025CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidancecited by 4
  17. 2024A Simple-but-effective Baseline for Training-free Class-Agnostic Countingcited by 3
  18. 2026Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Modelscited by 3
  19. 2024TFCounter:Polishing Gems for Training-Free Object Countingcited by 2
  20. 2024Mutually-Aware Feature Learning for Few-Shot Object Countingcited by 2
  21. 2025FiGO: Fine-Grained Object Counting without Annotationscited by 2
  22. 2025SDVPT: Semantic-Driven Visual Prompt Tuning for Open-World Object Countingcited by 2
  23. 2025SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insightscited by 2
  24. 2025Text-promptable Object Counting via Quantity Awareness Enhancementcited by 2
  25. 2026Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Countingcited by 2
  26. 2026Plant Taxonomy Meets Plant Counting: A Fine-Grained, Taxonomic Dataset for Counting Hundreds of Plant Speciescited by 2
  27. 2024Enhancing Zero-shot Counting via Language-guided Exemplar Learningcited by 1
  28. 2025Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localizationcited by 1
  29. 2025Expanding Zero-Shot Object Counting with Rich Promptscited by 1
  30. 2025Decoupling What to Count and Where to See for Referring Expression Countingcited by 1
  31. 2025Counting Through Occlusion: Framework for Open World Amodal Countingcited by 1
  32. 2025Object Counting with GPT-4o and GPT-5: A Comparative Studycited by 1
  33. 2025CoDi -- an exemplar-conditioned diffusion model for low-shot countingcited by 1
  34. 2026CountEx: Fine-Grained Counting via Exemplars and Exclusioncited by 1
  35. 2026Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Countingcited by 1
  36. 2026Count Anything at Any Granularitycited by 1
  37. 2026The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Countingcited by 1
  38. 2026Spatially-Aware Class-Agnostic Object Countingcited by 1

50 most cited of 65 All 65 (JSON)