Metraipolis › archive › dc_0730ff55b278
LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition — arXiv:2611.10321
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10321
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:42:22.360Z
- SHA-256 of the archived text
96eb9b0e486d4306abb0c9fd6894d22a2c3812b7c928ab2ae2a74860ba2e394f- Stable URL of this page
https://metraipolis.com/documento/dc_0730ff55b278
How to cite
LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition — arXiv:2611.10321 — arXiv (en), https://arxiv.org/abs/2611.10321 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0730ff55b278 (Metraipolis archive dc_0730ff55b278, sha256 96eb9b0e486d4306abb0c9fd6894d22a2c3812b7c928ab2ae2a74860ba2e394f)
BibTeX
@misc{dc0730ff55b278,
title = {LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition — arXiv:2611.10321},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10321},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0730ff55b278; sha256 96eb9b0e486d4306abb0c9fd6894d22a2c3812b7c928ab2ae2a74860ba2e394f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10321. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify all queried semantic concepts present in an image. Existing methods mainly improve global image-text matching or text-side representations, leaving local prediction largely under-explored. In this paper, we revisit local prediction and reveal that it can serve as a strong discriminative branch once two properties are properly handled: spatial consistency of local visual features and compatibility-aware local competition. This perspective is motivated by local semantic sparsity: each image region is related to only a small subset of queried concepts, while compatible concepts of different granularities or types may still coexist locally. We instantiate this perspective with LoCo, a selective Local Competition framework for OV-MLR. LoCo adopts a spatially consistent visual encoder to reduce local feature entanglement, and introduces Selective Softmax to impose competition only among locally incompatible categories while preserving compatible responses. Multi-scale inference further improves local prediction at different scales. LoCo can also be ensembled with an existing global predictor to provide complementary image-level context. Experiments on four multi-label benchmarks show that standalone LoCo improves average F1-score and mAP over TagCLIP by 3.4% and 3.8%, respectively. LoCo + DualPrompt achieves the highest averages among the compared methods, with gains of 4.8% and 5.2% over TagCLIP. Our results suggest that local semantic sparsity offers a useful basis for developing more discriminative open-vocabulary multi-label recognition methods. The code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.10321 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.582Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).