AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

CountEx: Fine-Grained Counting via Exemplars and Exclusion

Yifeng Huang, Gia Khanh Nguyen, Minh Hoai Nguyen

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Discriminative Query Refinement with exclusion prompts to LLMDetLLMDet · CoCount test (novel-category NC)MAE: 33.22 -> 26.61Improved
add Discriminative Query Refinement with exclusion prompts to LLMDetLLMDet · CoCount test (known-category KC)MAE: 16.82 -> 12.72Improved
subtract per-category density maps for negative exclusion instead of DQRLLMDet · CoCount test (novel-category NC)MAE: 33.22 -> 47.71Hurt
detection suppression for negatives instead of DQRLLMDet · CoCount test (known-category KC)MAE: 16.82 -> 16.94No clear effect
add selective query refinement stage (ablation)CountEx · CoCount test (known-category KC)MAE: 16.10 -> 12.72Improved
add shared feature identification stage (ablation)CountEx · CoCount test (known-category KC)MAE: 14.18 -> 12.72Improved
add exclusive feature extraction stage (ablation)CountEx · CoCount test (known-category KC)MAE: 13.40 -> 12.72Improved
add density prediction loss (ablation)CountEx · CoCount test (known-category KC)MAE: 15.20 -> 13.00Improved
add prototype losses (ablation)CountEx · CoCount test (known-category KC)MAE: 13.00 -> 12.72Improved
add negative text prompt (ablation)CountEx · CoCount test (known-category KC)MAE: 15.96 -> 13.22Improved
add negative exemplar boxes on top of negative text (ablation)CountEx · CoCount test (known-category KC)MAE: 13.22 -> 12.72Improved
use irrelevant negative prompt instead of none (ablation)CountEx · CoCount test (novel-category NC)MAE: 32.22 -> 28.43Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy