{"url":"/sota/zero-shot-learning-on-pascal-context","task":{"name":"Zero-Shot Learning","url":"/task/zero-shot-learning","note":null},"dataset":{"name":"PASCAL Context","url":"/dataset/pascal-context"},"category":"Computer Vision","categories":["Computer Vision","Methodology"],"category_note":null,"description":"**Zero-shot learning (ZSL)** is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning. \r\n\r\nEarlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning. \r\n\r\nBenchmark datasets for zero-shot learning include [aPY](/dataset/apy), [AwA](/dataset/awa2-1), and [CUB](/dataset/cub-200-2011), among others. \r\n\r\n( Image credit: [Prototypical Networks for Few shot Learning in PyTorch\r\n](https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch) )\r\n\r\nFurther readings:  \r\n\r\n- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://paperswithcode.com/paper/zero-shot-learning-a-comprehensive-evaluation)\r\n- [Zero-Shot Learning in Modern NLP](https://joeddav.github.io/blog/2020/05/29/ZSL.html)\r\n- [Zero-Shot Learning for Text Classification](https://amitness.com/2020/05/zero-shot-text-classification/)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["k=10 mIOU"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"k=10 mIOU":null}},"counts":{"rows":1,"rows_with_code":1,"rows_with_paper_page":1,"rows_dated":1,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ZS3Net","metrics":{"k=10 mIOU":"26.3"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600817","paper_url":"https://arxiv.org/abs/1906.00817v2","paper_title":"Zero-Shot Semantic Segmentation","code":"https://github.com/valeoai/ZS3","n_code_links":2,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":0,"rows_with_any_sample_ran":0,"distinct_papers_with_graph_line":0,"distinct_papers_with_any_sample_ran":0,"samples_over_distinct_papers":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":0,"n_unverified":0,"n_samples":0,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}