{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/progressive-semantic-guided-vision","title":"Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning","arxiv_id":"2404.07713","date":"2024-04-11","proceeding":"CVPR 2024 1","authors":["Shiming Chen","Wenjin Hou","Salman Khan","Fahad Shahbaz Khan"],"abstract":"Zero-shot learning (ZSL) recognizes the unseen classes by conducting visual-semantic interactions to transfer semantic knowledge from seen classes to unseen ones, supported by semantic information (e.g., attributes). However, existing ZSL methods simply extract visual features using a pre-trained network backbone (i.e., CNN or ViT), which fail to learn matched visual-semantic correspondences for representing semantic-related visual features as lacking of the guidance of semantic information, resulting in undesirable visual-semantic interactions. To tackle this issue, we propose a progressive semantic-guided vision transformer for zero-shot learning (dubbed ZSLViT). ZSLViT mainly considers two properties in the whole network: i) discover the semantic-related visual representations explicitly, and ii) discard the semantic-unrelated visual information. Specifically, we first introduce semantic-embedded token learning to improve the visual-semantic correspondences via semantic enhancement and discover the semantic-related visual tokens explicitly with semantic-guided token attention. Then, we fuse low semantic-visual correspondence visual tokens to discard the semantic-unrelated visual information for visual enhancement. These two operations are integrated into various encoders to progressively learn semantic-related visual representations for accurate visual-semantic interactions in ZSL. The extensive experiments show that our ZSLViT achieves significant performance gains on three popular benchmark datasets, i.e., CUB, SUN, and AWA2. Codes are available at: https://github.com/shiming-chen/ZSLViT .","url_abs":"https://arxiv.org/abs/2404.07713v2","url_pdf":"https://arxiv.org/pdf/2404.07713v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"progressive-semantic-guided-vision","repo_url":"https://github.com/shiming-chen/zslvit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.07713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07713"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shiming-chen/zslvit","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"66733f50aff69220","entry":"adjust_keep_rate","repo":"shiming-chen/zslvit","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66733f50aff69220"}},{"code_sha256_prefix":"63f355a22c4bfb43","entry":"compute_accuracy","repo":"shiming-chen/zslvit","repo_kind":"official","path":"train_function.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/train_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63f355a22c4bfb43"}},{"code_sha256_prefix":"39eace7e2822504f","entry":"drop_path","repo":"shiming-chen/zslvit","repo_kind":"official","path":"zslvit.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/zslvit.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39eace7e2822504f"}},{"code_sha256_prefix":"bf6cb2bcb5371413","entry":"get_reprs","repo":"shiming-chen/zslvit","repo_kind":"official","path":"train_function.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/train_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf6cb2bcb5371413"}},{"code_sha256_prefix":"191b2735955d18f4","entry":"resize_pos_embed","repo":"shiming-chen/zslvit","repo_kind":"official","path":"zslvit.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/zslvit.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"191b2735955d18f4"}},{"code_sha256_prefix":"e294b62d47bcc26f","entry":"speed_test","repo":"shiming-chen/zslvit","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e294b62d47bcc26f"}},{"code_sha256_prefix":"39d973f1e925c9a4","entry":"train","repo":"shiming-chen/zslvit","repo_kind":"official","path":"train_function.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/train_function.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39d973f1e925c9a4"}},{"code_sha256_prefix":"6d8a1f8a0697180f","entry":"checkpoint_filter_fn","repo":"shiming-chen/zslvit","repo_kind":"official","path":"zslvit.py","file_url":"https://github.com/shiming-chen/zslvit/blob/HEAD/zslvit.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d8a1f8a0697180f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}