Research

Paper

AI LLM March 23, 2026

Look, Listen and Segment: Towards Weakly Supervised Audio-visual Semantic Segmentation

Authors

Chengzhi Li, Heyan Huang, Ping Jian, Yanghao Zhou

Abstract

Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSAVSS), which uses only video-level labels to generate per-frame semantic masks of sounding objects. We decompose WSAVSS into looking, listening, and segmentation, and propose Progressive Cross-modal Alignment for Semantics (PCAS) with two modules: *Looking-before-Listening* and *Listening-before-Segmentation*. PCAS builds a classification task to train the audio-visual encoder using video labels, injects visual semantic prompts to enhance frame-level audio understanding, and then applies progressive contrastive alignment to map audio categories to image regions without mask annotations. Experiments show PCAS achieves state-of-the-art performance among weakly supervised methods on AVS and remains competitive with fully supervised baselines on AVSS, validating its effectiveness.

Metadata

arXiv ID: 2603.21948
Provider: ARXIV
Primary Category: cs.MM
Published: 2026-03-23
Fetched: 2026-03-24 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.21948v1</id>\n    <title>Look, Listen and Segment: Towards Weakly Supervised Audio-visual Semantic Segmentation</title>\n    <updated>2026-03-23T13:07:48Z</updated>\n    <link href='https://arxiv.org/abs/2603.21948v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.21948v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSAVSS), which uses only video-level labels to generate per-frame semantic masks of sounding objects. We decompose WSAVSS into looking, listening, and segmentation, and propose Progressive Cross-modal Alignment for Semantics (PCAS) with two modules: *Looking-before-Listening* and *Listening-before-Segmentation*. PCAS builds a classification task to train the audio-visual encoder using video labels, injects visual semantic prompts to enhance frame-level audio understanding, and then applies progressive contrastive alignment to map audio categories to image regions without mask annotations. Experiments show PCAS achieves state-of-the-art performance among weakly supervised methods on AVS and remains competitive with fully supervised baselines on AVSS, validating its effectiveness.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MM'/>\n    <published>2026-03-23T13:07:48Z</published>\n    <arxiv:comment>Accepted by ICASSP 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.MM'/>\n    <author>\n      <name>Chengzhi Li</name>\n    </author>\n    <author>\n      <name>Heyan Huang</name>\n    </author>\n    <author>\n      <name>Ping Jian</name>\n    </author>\n    <author>\n      <name>Yanghao Zhou</name>\n    </author>\n  </entry>"
}