Skip to main content
Search

# Open-Vocabulary Multi-Label Recognition

1 related articles

Subscribe to updates
  1. arXiv

    Local prediction stops being a side branch: LoCo lets only incompatible labels compete, beating TagCLIP by 3.4% average F1

    Open-vocabulary multi-label recognition has mostly been improved on the text side, with local prediction used only as a spatial repetition of image-level prediction. LoCo instead supplies local features through a spatially consistent visual encoder and applies a Selective Softmax that lets only locally incompatible categories compete while preserving compatible concepts, then adds multi-scale inference. On four multi-label benchmarks, standalone LoCo improves average F1 and mAP over TagCLIP by 3.4% and 3.8%; ensembled with DualPrompt's global predictions, it improves them by 4.8% and 5.2%.

You’re all caught up