HTTP/2 301 server: GitHub.com content-type: text/html location: https://yasserben.github.io/FLOSS/ access-control-allow-origin: * strict-transport-security: max-age=31556952 expires: Mon, 29 Dec 2025 22:39:19 GMT cache-control: max-age=600 x-proxy-cache: MISS x-github-request-id: 1B92:444BC:9684A3:A8D4D7:695300BE accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 22:29:19 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210098-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767047359.183549,VS0,VE202 vary: Accept-Encoding x-fastly-request-id: cec44b245a856fe0804816db99b5d7fae4920de5 content-length: 162 HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Mon, 17 Nov 2025 18:16:56 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"691b6698-24e9" expires: Mon, 29 Dec 2025 22:39:19 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: B5E2:2916CC:96BB78:A90CE5:695300BF accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 22:29:19 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210098-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767047359.399564,VS0,VE206 vary: Accept-Encoding x-fastly-request-id: a3cd18cf7365105b44a6fe06edf7cc3286ee3db7 content-length: 2676

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

Yasser Benigmim¹, Mohammad Fahes¹, Tuan-Hung Vu^1,2, Andrei Bursuc^1,2, Raoul de Charette¹

¹Inria ²Valeo.ai

Paper arXiv Code

TL;DR

• Focus: We challenge the conventional use of multiple templates in Open-Vocabulary Semantic Segmentation (OVSS) models.
• Key Finding: For each class, there exist single-template classifiers that significantly outperform the conventional averaged classifier.
• Our Approach: We propose FLOSS, a plug-and-play method that:
  • Identifies class-expert templates using prediction entropy
  • Requires no labels or additional training
  • Is complementary to existing OVSS methods
• Results: FLOSS consistently improves state-of-the-art methods on various OVSS benchmarks and generalizes well across datasets with distribution shifts.

Method

Recent Open-Vocabulary Semantic Segmentation (OVSS) models extend the CLIP model to segmentation while maintaining the use of multiple templates for constructing class-wise averaged text embeddings. Our method, FLOSS, challenges this approach by:

• Identifying single-template classifiers that outperform averaged classifiers
• Estimating class-experts using prediction entropy on unlabeled images
• Implementing a novel fusion method for more accurate OVSS predictions
• Providing improvements without requiring labels or additional training

Acknowledgements

This research was partially funded by the French Agence Nationale de la Recherche (ANR) with the project SIGHT (ANR-20-CE23-0016). We sincerely thank Telecom Paris for providing the resources necessary to run our experiments and Nacereddine Laddaoui for his invaluable help with infrastructure. We are also grateful to Ivan Lopes for proofreading.

BibTeX

@misc{benigmim2025flossfreelunchopenvocabulary,
      title={FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation},
      author={Yasser Benigmim and Mohammad Fahes and Tuan-Hung Vu and Andrei Bursuc and Raoul de Charette},
      year={2025},
      eprint={2504.10487},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2504.10487},
}