Research

Paper

AI LLM February 26, 2026

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

Authors

Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos Tolias

Abstract

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.

Metadata

arXiv ID: 2602.23339
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-26
Fetched: 2026-02-27 04:35

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.23339v1</id>\n    <title>Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?</title>\n    <updated>2026-02-26T18:45:33Z</updated>\n    <link href='https://arxiv.org/abs/2602.23339v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.23339v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two challenges: the coarse image-level supervision used to train VLMs and the semantic ambiguity of natural language. We address these limitations by introducing a few-shot setting that augments textual prompts with a support set of pixel-annotated images. Building on this, we propose a retrieval-augmented test-time adapter that learns a lightweight, per-image classifier by fusing textual and visual support features. Unlike prior methods relying on late, hand-crafted fusion, our approach performs learned, per-query fusion, achieving stronger synergy between modalities. The method supports continually expanding support sets, and applies to fine-grained tasks such as personalized segmentation. Experiments show that we significantly narrow the gap between zero-shot and supervised segmentation while preserving open-vocabulary ability.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-26T18:45:33Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Tilemachos Aravanis</name>\n    </author>\n    <author>\n      <name>Vladan Stojnić</name>\n    </author>\n    <author>\n      <name>Bill Psomas</name>\n    </author>\n    <author>\n      <name>Nikos Komodakis</name>\n    </author>\n    <author>\n      <name>Giorgos Tolias</name>\n    </author>\n  </entry>"
}