One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jo, Sanghyun, Lee, Seo Jin, Hong, Seohyung, Gang, Yoorim, Kim, Hyeongsub, Seo, Hyungseok, Kim, Kyungsu
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917543051001856
author Jo, Sanghyun
Lee, Seo Jin
Hong, Seohyung
Gang, Yoorim
Kim, Hyeongsub
Seo, Hyungseok
Kim, Kyungsu
author_facet Jo, Sanghyun
Lee, Seo Jin
Hong, Seohyung
Gang, Yoorim
Kim, Hyeongsub
Seo, Hyungseok
Kim, Kyungsu
contents Cell instance segmentation models trained on cell-specific datasets suffer severe performance drops on out-of-distribution cell types, while interactive foundation models overcome this through per-instance prompting at a cost that is prohibitively expensive for histopathology images containing hundreds to thousands of densely packed instances. We introduce Group Prompting, a new paradigm that shifts interactive segmentation from per-instance $O(N)$ to per-type $O(T)$, where a single click per cell type suffices to segment all instances of that type. Our key observation is that the frozen image encoder of the Segment Anything Model (SAM) already clusters same-type cells in its feature space before any prompt is given. Exploiting this property, we propose Chain-of-Prompts (CoP), a training-free framework that recursively expands a single user click by (1) identifying reliable same-type locations through non-parametric gating of multi-scale encoder features, and (2) selecting the most spatially distant reliable point as the next prompt to maximize coverage. On three cell-type-annotated benchmarks, CoP with one click per type retains over 90% of per-instance performance and surpasses fully-supervised methods without any additional training. On four morphologically homogeneous benchmarks, a single click retains over 99%. Project Page: https://shjo-april.github.io/Chain-of-Prompts/
format Preprint
id arxiv_https___arxiv_org_abs_2605_29429
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
Jo, Sanghyun
Lee, Seo Jin
Hong, Seohyung
Gang, Yoorim
Kim, Hyeongsub
Seo, Hyungseok
Kim, Kyungsu
Computer Vision and Pattern Recognition
Cell instance segmentation models trained on cell-specific datasets suffer severe performance drops on out-of-distribution cell types, while interactive foundation models overcome this through per-instance prompting at a cost that is prohibitively expensive for histopathology images containing hundreds to thousands of densely packed instances. We introduce Group Prompting, a new paradigm that shifts interactive segmentation from per-instance $O(N)$ to per-type $O(T)$, where a single click per cell type suffices to segment all instances of that type. Our key observation is that the frozen image encoder of the Segment Anything Model (SAM) already clusters same-type cells in its feature space before any prompt is given. Exploiting this property, we propose Chain-of-Prompts (CoP), a training-free framework that recursively expands a single user click by (1) identifying reliable same-type locations through non-parametric gating of multi-scale encoder features, and (2) selecting the most spatially distant reliable point as the next prompt to maximize coverage. On three cell-type-annotated benchmarks, CoP with one click per type retains over 90% of per-instance performance and surpasses fully-supervised methods without any additional training. On four morphologically homogeneous benchmarks, a single click retains over 99%. Project Page: https://shjo-april.github.io/Chain-of-Prompts/
title One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.29429