Enregistré dans:
Détails bibliographiques
Auteurs principaux: Espinosa, Miguel, Yang, Chenhongyi, Ericsson, Linus, McDonagh, Steven, Crowley, Elliot J.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2507.02798
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914302523342848
author Espinosa, Miguel
Yang, Chenhongyi
Ericsson, Linus
McDonagh, Steven
Crowley, Elliot J.
author_facet Espinosa, Miguel
Yang, Chenhongyi
Ericsson, Linus
McDonagh, Steven
Crowley, Elliot J.
contents The performance of image segmentation models has historically been constrained by the high cost of collecting large-scale annotated data. The Segment Anything Model (SAM) alleviates this original problem through a promptable, semantics-agnostic, segmentation paradigm and yet still requires manual visual-prompts or complex domain-dependent prompt-generation rules to process a new image. Towards reducing this new burden, our work investigates the task of object segmentation when provided with, alternatively, only a small set of reference images. Our key insight is to leverage strong semantic priors, as learned by foundation models, to identify corresponding regions between a reference and a target image. We find that correspondences enable automatic generation of instance-level segmentation masks for downstream tasks and instantiate our ideas via a multi-stage, training-free method incorporating (1) memory bank construction; (2) representation aggregation and (3) semantic-aware feature matching. Our experiments show significant improvements on segmentation metrics, leading to state-of-the-art performance on COCO FSOD (36.8% nAP), PASCAL VOC Few-Shot (71.2% nAP50) and outperforming existing training-free approaches on the Cross-Domain FSOD benchmark (22.4% nAP).
format Preprint
id arxiv_https___arxiv_org_abs_2507_02798
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle No time to train! Training-Free Reference-Based Instance Segmentation
Espinosa, Miguel
Yang, Chenhongyi
Ericsson, Linus
McDonagh, Steven
Crowley, Elliot J.
Computer Vision and Pattern Recognition
The performance of image segmentation models has historically been constrained by the high cost of collecting large-scale annotated data. The Segment Anything Model (SAM) alleviates this original problem through a promptable, semantics-agnostic, segmentation paradigm and yet still requires manual visual-prompts or complex domain-dependent prompt-generation rules to process a new image. Towards reducing this new burden, our work investigates the task of object segmentation when provided with, alternatively, only a small set of reference images. Our key insight is to leverage strong semantic priors, as learned by foundation models, to identify corresponding regions between a reference and a target image. We find that correspondences enable automatic generation of instance-level segmentation masks for downstream tasks and instantiate our ideas via a multi-stage, training-free method incorporating (1) memory bank construction; (2) representation aggregation and (3) semantic-aware feature matching. Our experiments show significant improvements on segmentation metrics, leading to state-of-the-art performance on COCO FSOD (36.8% nAP), PASCAL VOC Few-Shot (71.2% nAP50) and outperforming existing training-free approaches on the Cross-Domain FSOD benchmark (22.4% nAP).
title No time to train! Training-Free Reference-Based Instance Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.02798