mlsanityData to 7 Oct 2026

CountCLIP -- [Re] Teaching CLIP to Count to Ten

arXiv 2406.03586 ↗First posted 5 Jun 2024cs.CV cs.AI cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Large vision-language models (VLMs) are shown to learn rich joint image-text representations enabling high performances in relevant downstream tasks. However, they fail to showcase their quantitative understanding of objects, and they lack good counting-aware representation. This paper conducts a reproducibility study of 'Teaching CLIP to Count to Ten' (Paiss et al., 2023), which presents a method to finetune a CLIP model (Radford et al., 2021) to improve zero-shot counting accuracy in an image while maintaining the performance for zero-shot classification by introducing a counting-contrastive loss term. We improve the model's performance on a smaller subset of their training data with lower computational resources. We verify these claims by reproducing their study with our own code. The implementation can be found at https://github.com/SforAiDl/CountCLIP.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 6 of its 7 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

6 of 7 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Teaching CLIP to Count to Ten23 Feb

Other references · 5

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  3. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  4. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 450
  5. 2021Combined Scaling for Zero-shot Transfer Learningcited by 182

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
  2. 2025Object Counting with GPT-4o and GPT-5: A Comparative Study
  3. 2023Zero-Shot Object Counting with Language-Vision Models
  4. 2025T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
  5. 2025Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting
  6. 2024LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models
  7. 2025Assessing the Visual Enumeration Abilities of Specialized Counting Architectures and Vision-Language Models
  8. 2024Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition