{"url":"/task/multi-label-zero-shot-learning","name":"Multi-label zero-shot learning","slug":"multi-label-zero-shot-learning","description_markdown":"The goal of multi-label classification task is to predict a set of labels in an image. As an extension of zero-shot learning (ZSL), multi-label zero-shot learning (ML-ZSL) is developed to identify multiple seen and unseen labels in an image.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":27,"papers_with_code":15,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-label-zero-shot-learning-on-nus-wide","slug":"multi-label-zero-shot-learning-on-nus-wide","dataset":"NUS-WIDE","dataset_url":"/dataset/nus-wide","rows_in_archive":10,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MKT(CLIP)","paper_title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","paper_url":"/paper/open-vocabulary-multi-label-classification","paper_date":"2022-07-05","arxiv_id":"2207.01887","code_links":[{"title":"sunanhe/mkt","url":"https://github.com/sunanhe/mkt"}],"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-label-zero-shot-learning-on-open-images","slug":"multi-label-zero-shot-learning-on-open-images","dataset":"Open Images V4","dataset_url":"/dataset/open-images-v4","rows_in_archive":8,"metrics":["MAP"],"first_row_in_archive_order":{"model":"MKT(IN-1K)","paper_title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","paper_url":"/paper/open-vocabulary-multi-label-classification","paper_date":"2022-07-05","arxiv_id":"2207.01887","code_links":[{"title":"sunanhe/mkt","url":"https://github.com/sunanhe/mkt"}],"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/multi-label-zero-shot-learning-on-imagenet-1k","slug":"multi-label-zero-shot-learning-on-imagenet-1k","dataset":"ImageNet-1k to MSCOCO","dataset_url":null,"rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"ADDS","paper_title":"Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features","paper_url":"/paper/a-dual-modality-approach-for-zero-shot-multi","paper_date":"2022-08-19","arxiv_id":"2208.09562","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/nus-wide","name":"NUS-WIDE","full_name":"","num_papers_in_archive":348},{"url":"/dataset/open-images-v4","name":"Open Images V4","full_name":"","num_papers_in_archive":37}],"subtasks":[],"parent_tasks":[{"url":"/task/zero-shot-learning","name":"Zero-Shot Learning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":15,"of":15,"tagged_in_all":27,"items":[{"url":"/paper/label-embedding-for-image-classification","title":"Label-Embedding for Image Classification","date":"2015-03-30","arxiv_id":"1503.08677","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-learning-by-convex-combination-of","title":"Zero-Shot Learning by Convex Combination of Semantic Embeddings","date":"2013-12-19","arxiv_id":"1312.5650","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/clip-decoder-zeroshot-multilabel","title":"CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation","date":"2024-06-21","arxiv_id":"2406.14830","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/pseudo-prompt-generating-in-pre-trained","title":"Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification","date":"2024-05-10","arxiv_id":"2405.06468","repositories_listed":1,"syntology":null},{"url":"/paper/label-propagation-for-zero-shot","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","date":"2024-04-05","arxiv_id":"2404.04072","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/open-vocabulary-multi-label-classification","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","date":"2022-07-05","arxiv_id":"2207.01887","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/ml-decoder-scalable-and-versatile","title":"ML-Decoder: Scalable and Versatile Classification Head","date":"2021-11-25","arxiv_id":"2111.12933","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/discriminative-region-based-multi-label-zero","title":"Discriminative Region-based Multi-Label Zero-Shot Learning","date":"2021-08-20","arxiv_id":"2108.09301","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/contrastive-language-image-pre-training-for","title":"Contrastive Language-Image Pre-training for the Italian Language","date":"2021-08-19","arxiv_id":"2108.08688","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-diversity-learning-for-zero-shot","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","date":"2021-05-12","arxiv_id":"2105.05926","repositories_listed":1,"syntology":null},{"url":"/paper/generative-multi-label-zero-shot-learning","title":"Generative Multi-Label Zero-Shot Learning","date":"2021-01-27","arxiv_id":"2101.11606","repositories_listed":1,"syntology":null},{"url":"/paper/interaction-compass-multi-label-zero-shot","title":"Interaction Compass: Multi-Label Zero-Shot Learning of Human-Object Interactions via Spatial Relations","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-shared-multi-attention-framework-for-multi","title":"A Shared Multi-Attention Framework for Multi-Label Zero-Shot Learning","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-learning-for-audio-based-music","title":"Zero-shot Learning for Audio-based Music Classification and Tagging","date":"2019-07-05","arxiv_id":"1907.02670","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/multi-label-zero-shot-learning-with","title":"Multi-Label Zero-Shot Learning with Structured Knowledge Graphs","date":"2017-11-17","arxiv_id":"1711.06526","repositories_listed":1,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}