cs.CVNov 6, 2026

LoCo: Selective Local Competition for Discriminative Open-Vocabulary Multi-Label Recognition

Authors: Zhuoming Li, Bo Han, Xiaoyu Wang, Yuheng Jia

Organizations: School of Software Engineering, Southeast University, Nanjing, China · School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China

Abstract

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 https://github.com/lee-plus-plus/LoCo.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A novel Framework for Open-Vocabulary Multi-Object Recognition using CLIP

    Mar 6, 2026Wei Yu Chen, Ying DaiOpen-Vocabulary Object DetectionVision-Language Alignment

  2. CorrCLIPv2: Harnessing Unlabeled Images for Open-Vocabulary Semantic Segmentation

    Oct 17, 2026Dengke Zhang, Fagui Liu, Quan Tang +1Open-Vocabulary Semantic SegmentationSemantic Segmentation

  3. MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection

    Oct 16, 2025Hojun Choi, Youngsun Lim, Jaeyo Shin +1Open-Vocabulary Object DetectionVisual Reasoning