AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Enhancing Zero-shot Object Counting via Text-guided Local Ranking and Number-evoked Global Attention

Shiwei Zhang, Qi Zhou, Wei Ke

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 3 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 Text-guided Local Ranking (ablation)ClipCount · FSC-147 testMAE: 17.45 -> 16.71Improved
add Number-evoked Global Attention (ablation)ClipCount · FSC-147 testMAE: 17.45 -> 16.81Improved
add both TLR and NGA (ablation)ClipCount · FSC-147 valMAE: 18.93 -> 17.52Improved
use coarse-to-fine number prompts instead of coarse only (ablation)ClipCount+Ours · FSC-147 valMAE: 18.17 -> 17.52Improved
apply strategy to ClipCountClipCount · FSC-147 testRMSE: 104.88 -> 100.63Improved
apply strategy to VLCounterVLCounter · FSC-147 testRMSE: 106.16 -> 107.47Hurt
apply strategy to GDino (w/ finetune)GDino finetune · FSC-147 testRMSE: 104.98 -> 106.5Hurt
apply strategy to CountGDCountGD · FSC-147 testMAE: 14.76 -> 12.84Improved
apply strategy to GDino finetuneGDino finetune · ZSC-8K valMAE: 13.92 -> 11.17Improved
apply strategy to ClipCountClipCount · ZSC-8K testlongtailMAE: 22.65 -> 21.90Improved
apply strategy to ClipCount, evaluate cross-datasetClipCount · ShanghaiTech Part A (from FSC-147)MAE: 192.6 -> 176.24Improved
set delta to 0.5 instead of 0.1 or 0.9 (ablation)ClipCount+Ours · FSC-147MAEImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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