AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Zero-shot Object Counting with Good Exemplars

Huilin Zhu, Jingling Yuan, Zhengwei Yang, Yu Guo, Xian Zhong, Zheng Wang, Shengfeng He

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 28 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 single-object exemplar filter to Grounding DINO (ablation)Grounding DINO · CARPKMAE: 29.72 -> 18.54Improved
add single-object filter without training the counter (ablation)Grounding DINO exemplars · FSC-147 testMAE: 54.48 -> 54.27No clear effect
add density loss training (ablation)Grounding DINO + filter · FSC-147 testMAE: 54.27 -> 18.93Improved
add contrastive loss with negative exemplars (ablation)VA-Count · FSC-147MAE (val/test) and RMSE (test): val MAE 19.63 -> 17.87; test MAE 18.93 -> 17.88; test RMSE 116.65 -> 129.31Mixed
set IoU threshold for negative exemplars to 0.5 rather than extremes (ablation)VA-Count · FSC-147 valMAE: 0.1: 18.83; 0.9: 22.30; 0.5: 17.87Improved
set Grounding DINO logits threshold to 0.02 rather than 0.01 or 0.05 (ablation)VA-Count · FSC-147 valMAE: 0.01: 27.36; 0.05: 25.60; 0.02: 17.87Improved
zero-shot VA-Count versus other zero-shot methodsVA-Count · FSC-147MAE/RMSE: val MAE 17.87 vs 18.79 (CLIP-Count); test RMSE 129.31 vs 106.62Mixed
zero-shot VA-Count transfer without fine-tuning to crowd dataVA-Count · FSC-147 to ShanghaiTech BMAE: 66.6 -> 40.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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