mlsanityData to 14 Oct 2026

Exemplar Free Class Agnostic Counting

arXiv 2205.14212 ↗First posted 27 May 2022cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a fully automated setting, and require computationally expensive test time adaptation. To address these challenges, we propose a visual counter which operates in a fully automated setting and does not require any test time adaptation. Our proposed approach first identifies exemplars from repeating objects in an image, and then counts the repeating objects. We propose a novel region proposal network for identifying the exemplars. After identifying the exemplars, we obtain the corresponding count by using a density estimation based Visual Counter. We evaluate our proposed approach on FSC-147 dataset, and show that it achieves superior performance compared to the existing approaches.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

33 of 47 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2017Mask R-CNNcited by 7,277
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  9. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  10. 2018Zero-Shot Object Detectioncited by 189
  11. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  12. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
21 more
  1. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  2. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  3. 2018Context-Aware Crowd Countingcited by 150
  4. 2021Learning To Count Everythingcited by 150
  5. 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
  6. 2020JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Methodcited by 109
  7. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  8. 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
  9. 2018Class-Agnostic Countingcited by 85
  10. 2020Localization in the Crowd with Topological Constraintscited by 68
  11. 2016One-shot Learning with Memory-Augmented Neural Networkscited by 60
  12. 2018Leveraging Unlabeled Data for Crowd Counting by Learning to Rankcited by 57
  13. 2018Revisiting Perspective Information for Efficient Crowd Countingcited by 49
  14. 2018Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Conceptscited by 48
  15. 2018Iterative Crowd Countingcited by 48
  16. 2020Semi-Supervised Crowd Counting via Self-Training on Surrogate Taskscited by 35
  17. 2018Zero-Shot Detectioncited by 27
  18. 2021Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Countingcited by 20
  19. 2018Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNNcited by 19
  20. 2020Uncertainty Estimation and Sample Selection for Crowd Countingcited by 11
  21. 2019Crowd Transformer Networkcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 7; 2025: 7; 2026: 5.

32 papers.

Sort:

By area:

  1. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 83
  2. 2022CounTR: Transformer-based Generalised Visual Countingcited by 79
  3. 2022A Low-Shot Object Counting Network With Iterative Prototype Adaptationcited by 65
  4. 2023Zero-shot Object Countingcited by 57
  5. 2024DAVE -- A Detect-and-Verify Paradigm for Low-Shot Countingcited by 49
  6. 2023Open-world Text-specified Object Countingcited by 41
  7. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  8. 2023Training-free Object Counting with Promptscited by 34
  9. 2023Counting Guidance for High Fidelity Text-to-Image Synthesiscited by 24
  10. 2024Zero-shot Object Counting with Good Exemplarscited by 21
  11. 2024A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentationcited by 21
  12. 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Countingcited by 19
20 more
  1. 2024OmniCount: Multi-label Object Counting with Semantic-Geometric Priorscited by 16
  2. 2023ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Countingcited by 13
  3. 2023Zero-Shot Object Counting with Language-Vision Modelscited by 9
  4. 2023Interactive Class-Agnostic Object Countingcited by 8
  5. 2025A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approachescited by 7
  6. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluationcited by 7
  7. 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matchingcited by 6
  8. 2023SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Networkcited by 5
  9. 2023GCNet: Probing Self-Similarity Learning for Generalized Counting Networkcited by 4
  10. 2024TFCounter:Polishing Gems for Training-Free Object Countingcited by 2
  11. 2025Text-promptable Object Counting via Quantity Awareness Enhancementcited by 2
  12. 2024Enhancing Zero-shot Counting via Language-guided Exemplar Learningcited by 1
  13. 2025CoDi -- an exemplar-conditioned diffusion model for low-shot countingcited by 1
  14. 2026OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Countingcited by 1
  15. 2026CountEx: Fine-Grained Counting via Exemplars and Exclusioncited by 1
  16. 2026Spatially-Aware Class-Agnostic Object Countingcited by 1
  17. 2024GCA-SUNet: A Gated Context-Aware Swin-UNet for Exemplar-Free Countingcited by 0
  18. 2025CountFormer: A Transformer Framework for Learning Visual Repetition and Structure in Class-Agnostic Object Countingcited by 0
  19. 2026Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesiscited by 0
  20. 2026DualCount: Structurally Consistent Density and Point Modeling for Zero-Shot Object Countingcited by 0