mlsanityData to 14 Oct 2026

OmniCount: Multi-label Object Counting with Semantic-Geometric Priors

arXiv 2403.05435 ↗First posted 8 Mar 2024cs.CV eess.IV eess.SPcited by 16

Not on the map. Why?

Abstract (arXiv)

Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies come with their own set of limitations, such as the need for manual exemplar input and multiple passes for multiple categories, resulting in significant inefficiencies. This paper introduces a more practical approach enabling simultaneous counting of multiple object categories using an open-vocabulary framework. Our solution, OmniCount, stands out by using semantic and geometric insights (priors) from pre-trained models to count multiple categories of objects as specified by users, all without additional training. OmniCount distinguishes itself by generating precise object masks and leveraging varied interactive prompts via the Segment Anything Model for efficient counting. To evaluate OmniCount, we created the OmniCount-191 benchmark, a first-of-its-kind dataset with multi-label object counts, including points, bounding boxes, and VQA annotations. Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions. The project webpage is available at https://mondalanindya.github.io/OmniCount.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 60 of its 79 references that are in the map. First posted on arXiv 8 Mar 2024.

Builds on

60 of 79 references.

References · 60

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2023Segment Anythingcited by 8,234
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  8. 2015VQA: Visual Question Answeringcited by 2,506
  9. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  10. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  11. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  12. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 565
38 more
  1. 2021Image Segmentation Using Text and Image Promptscited by 512
  2. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  3. 2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 300
  4. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  5. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  6. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  7. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 174
  8. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  9. 2022SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentationcited by 164
  10. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 156
  11. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  12. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  13. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  14. 2021Learning To Count Everythingcited by 150
  15. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  16. 2020JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Methodcited by 109
  17. 2018Class-Agnostic Countingcited by 85
  18. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 83
  19. 2022Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Countingcited by 80
  20. 2023SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anythingcited by 75
  21. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  22. 2023Zero-shot Object Countingcited by 57
  23. 2016Visual Question Answering: Datasets, Algorithms, and Future Challengescited by 56
  24. 2022Rethinking Spatial Invariance of Convolutional Networks for Object Countingcited by 54
  25. 2022Grounding Answers for Visual Questions Asked by Visually Impaired Peoplecited by 47
  26. 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Modelcited by 47
  27. 2023STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learningcited by 41
  28. 2023Point-Query Quadtree for Crowd Counting, Localization, and Morecited by 40
  29. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  30. 2019Object Counting and Instance Segmentation with Image-level Supervisioncited by 36
  31. 2019Learning Spatial Awareness to Improve Crowd Countingcited by 36
  32. 2016Counting Everyday Objects in Everyday Scenescited by 34
  33. 2023Training-free Object Counting with Promptscited by 34
  34. 2019Counting with Focus for Freecited by 33
  35. 2019Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Methodcited by 32
  36. 2022Exemplar Free Class Agnostic Countingcited by 32
  37. 2018Finding any Waldo: zero-shot invariant and efficient visual searchcited by 28
  38. 2017Dynamic Zoom-in Network for Fast Object Detection in Large Imagescited by 23

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 7.

16 papers.

Sort:

By area:

  1. 2024Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Countingcited by 11
  2. 2025CountGD++: Generalized Prompting for Open-World Countingcited by 8
  3. 2025A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approachescited by 7
  4. 2025Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluationcited by 7
  5. 2025CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbonescited by 6
  6. 2025CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidancecited by 4
  7. 2025SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insightscited by 2
  8. 2025Semi-Supervised Multi-View Crowd Counting by Ranking Multi-View Fusion Modelscited by 2
  9. 2026Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Countingcited by 2
  10. 2026OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Countingcited by 1
  11. 2026Count Anything at Any Granularitycited by 1
  12. 2026The MixCount Dataset: Bridging the Data Gap for Open-Vocabulary Object Countingcited by 1
4 more
  1. 2026AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Countingcited by 1
  2. 2025CountZES: Counting via Zero-Shot Exemplar Selectioncited by 0
  3. 2026Count Anythingcited by 0
  4. 2026Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challengescited by 0