AI Paper Atlas

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

Unleashing the Power of Prompt-driven Nucleus Instance Segmentation

Zhongyi Shui, Yunlong Zhang, Kai Yao, Chenglu Zhu, Sunyi Zheng, Jingxiong Li, Honglin Li, YUXUAN SUN, Ruizhe Guo, Lin Yang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 29 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
fine-tune SAM on nucleus data (one-prompt-one-nucleus) (ablation)SAM-H with prompter · CPM-17PQ: 0.223 -> 0.723Improved
add auxiliary nuclear region segmentation task to prompter (ablation)PromptNucSeg-H · CPM-17PQ: 0.723 -> 0.727Improved
add mask-aided prompt filtering at inference (ablation)PromptNucSeg-H · CPM-17PQ: 0.727 -> 0.731Improved
add one adjacent-nucleus negative prompt in training and testing (ablation)PromptNucSeg-H · CPM-17 (predicted prompts)PQ: 0.731 -> 0.733Improved
add negative prompts only at test time (not in fine-tuning) (ablation)PromptNucSeg-H · CPM-17 (predicted prompts)PQ: 0.731 -> 0.730No clear effect
include negative prompts during fine-tuning (1 negative) (ablation)PromptNucSeg-H with GT prompts · CPM-17 (oracle GT prompts)PQ: 0.782 -> 0.790Improved
increase negative prompts from 1 to 2 with predicted (noisy) prompts (ablation)PromptNucSeg-H · CPM-17 (predicted prompts)PQ: 0.733 -> 0.729Hurt
increase negative prompts from 1 to 2 with ground-truth prompts (ablation)PromptNucSeg-H · CPM-17 (oracle GT prompts)PQ: 0.790 -> 0.796Improved
let prompter rather than segmentor do nucleus classification (ablation)PromptNucSeg-H · PanNukemPQ: 0.506 -> 0.512Improved
use PromptNucSeg-H instead of best prior methodsnucleus instance segmentation · PanNukemPQ: 0.4980 -> 0.5123Improved

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