mlsanityData to 14 Oct 2026

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation

arXiv 2508.00728 ↗First posted 1 Aug 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose YOLO-Count, a differentiable open-vocabulary object counting model that tackles both general counting challenges and enables precise quantity control for text-to-image (T2I) generation. A core contribution is the 'cardinality' map, a novel regression target that accounts for variations in object size and spatial distribution. Leveraging representation alignment and a hybrid strong-weak supervision scheme, YOLO-Count bridges the gap between open-vocabulary counting and T2I generation control. Its fully differentiable architecture facilitates gradient-based optimization, enabling accurate object count estimation and fine-grained guidance for generative models. Extensive experiments demonstrate that YOLO-Count achieves state-of-the-art counting accuracy while providing robust and effective quantity control for T2I systems.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

43 of 54 references.

References · 43

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  4. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  6. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  7. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,464
  8. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  9. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  10. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  11. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 503
  12. 2023Universal Guidance for Diffusion Modelscited by 437
31 more
  1. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 359
  2. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 294
  3. 2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusioncited by 282
  4. 2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generationcited by 259
  5. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 228
  6. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  7. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 156
  8. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  9. 2021Learning To Count Everythingcited by 150
  10. 2024Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editingcited by 135
  11. 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 124
  12. 2024InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimizationcited by 123
  13. 2024Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detectioncited by 122
  14. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Countingcited by 83
  15. 2022CounTR: Transformer-based Generalised Visual Countingcited by 79
  16. 2023Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Followingcited by 77
  17. 2024CountGD: Multi-Modal Open-World Countingcited by 59
  18. 2023Zero-shot Object Countingcited by 57
  19. 2022Few-shot Object Counting and Detectioncited by 55
  20. 2024DAVE -- A Detect-and-Verify Paradigm for Low-Shot Countingcited by 49
  21. 2024Make It Count: Text-to-Image Generation with an Accurate Number of Objectscited by 47
  22. 2023VLCounter: Text-aware Visual Representation for Zero-Shot Object Countingcited by 45
  23. 2022Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervisioncited by 41
  24. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  25. 2023Counting Guidance for High Fidelity Text-to-Image Synthesiscited by 24
  26. 2023LoCo: Locally Constrained Training-Free Layout-to-Image Synthesiscited by 21
  27. 2024Zero-shot Object Counting with Good Exemplarscited by 21
  28. 2023Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Modelscited by 19
  29. 2023Regressor-Segmenter Mutual Prompt Learning for Crowd Countingcited by 16
  30. 2023Focus for Free in Density-Based Countingcited by 8
  31. 2024QUOTA: Quantifying Objects with Text-to-Image Models for Any Domaincited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 6.

10 papers.

  1. 2025OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlapscited by 10
  2. 2025C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editingcited by 5
  3. 2025CountLoop: Training-Free High-Instance Image Generation via Iterative Agent Guidancecited by 4
  4. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  5. 2025CoDi -- an exemplar-conditioned diffusion model for low-shot countingcited by 1
  6. 2026Soft Tail-dropping for Adaptive Visual Tokenizationcited by 1
  7. 2026AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Countingcited by 1
  8. 2026ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Modelscited by 0
  9. 2026Count Anythingcited by 0
  10. 2026Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challengescited by 0