{"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/latent-embedding-feedback-and-discriminative","title":"Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification","arxiv_id":"2003.07833","date":"2020-03-17","proceeding":"ECCV 2020 8","authors":["Sanath Narayan","Akshita Gupta","Fahad Shahbaz Khan","Cees G. M. Snoek","Ling Shao"],"abstract":"Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative Adversarial Networks that synthesize unseen class features by leveraging class-specific semantic embeddings. During training, they generate semantically consistent features, but discard this constraint during feature synthesis and classification. We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature synthesis and classification. We first introduce a feedback loop, from a semantic embedding decoder, that iteratively refines the generated features during both the training and feature synthesis stages. The synthesized features together with their corresponding latent embeddings from the decoder are then transformed into discriminative features and utilized during classification to reduce ambiguities among categories. Experiments on (generalized) zero-shot object and action classification reveal the benefit of semantic consistency and iterative feedback, outperforming existing methods on six zero-shot learning benchmarks. Source code at https://github.com/akshitac8/tfvaegan.","url_abs":"https://arxiv.org/abs/2003.07833v2","url_pdf":"https://arxiv.org/pdf/2003.07833v2.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":"latent-embedding-feedback-and-discriminative","repo_url":"https://github.com/akshitac8/tfvaegan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"generalized-zero-shot-learning","task_name":"Generalized Zero-Shot Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-zero-shot-learning-on-awa2","task":"Generalized Zero-Shot Learning","dataset":"AwA2","model":"GZSL_TF-VAEGAN","rank_in_archive_order":3,"of":4,"metrics":{"Harmonic mean":"66.6"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-cub-200","task":"Generalized Zero-Shot Learning","dataset":"CUB-200-2011","model":"GZSL_TF-VAEGAN","rank_in_archive_order":3,"of":3,"metrics":{"Harmonic mean":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-oxford-102-1","task":"Generalized Zero-Shot Learning","dataset":"Oxford 102 Flower","model":"GZSL_TF-VAEGAN","rank_in_archive_order":2,"of":2,"metrics":{"Harmonic mean":"71.7"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-sun","task":"Generalized Zero-Shot Learning","dataset":"SUN Attribute","model":"GZSL_TF-VAEGAN","rank_in_archive_order":3,"of":9,"metrics":{"Harmonic mean":"43"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-awa2","task":"Zero-Shot Learning","dataset":"AwA2","model":"ZSL_TF-VAEGAN","rank_in_archive_order":3,"of":4,"metrics":{"average top-1 classification accuracy":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-cub-200-2011","task":"Zero-Shot Learning","dataset":"CUB-200-2011","model":"ZSL_TF-VAEGAN","rank_in_archive_order":5,"of":14,"metrics":{"average top-1 classification accuracy":"64.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-oxford-102-flower","task":"Zero-Shot Learning","dataset":"Oxford 102 Flower","model":"ZSL_TF-VAEGAN","rank_in_archive_order":2,"of":2,"metrics":{"average top-1 classification accuracy":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-sun-attribute","task":"Zero-Shot Learning","dataset":"SUN Attribute","model":"ZSL_TF-VAEGAN","rank_in_archive_order":3,"of":9,"metrics":{"average top-1 classification accuracy":"66"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2003.07833","atlas_url":"https://app.syntology.ai/?focus=2003.07833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07833"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/akshitac8/tfvaegan","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"ran_violates":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"167cb4b4ad32f511","entry":"WeightedL1","repo":"akshitac8/tfvaegan","repo_kind":"official","path":"train_actions.py","file_url":"https://github.com/akshitac8/tfvaegan/blob/HEAD/train_actions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"167cb4b4ad32f511"}},{"code_sha256_prefix":"3bb6f4b7a7021d0f","entry":"WeightedL1","repo":"akshitac8/tfvaegan","repo_kind":"official","path":"train_images.py","file_url":"https://github.com/akshitac8/tfvaegan/blob/HEAD/train_images.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bb6f4b7a7021d0f"}},{"code_sha256_prefix":"aaa55fee4c12babe","entry":"loss_fn","repo":"akshitac8/tfvaegan","repo_kind":"official","path":"train_actions.py","file_url":"https://github.com/akshitac8/tfvaegan/blob/HEAD/train_actions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aaa55fee4c12babe"}},{"code_sha256_prefix":"7ac965f971d0020b","entry":"map_label","repo":"akshitac8/tfvaegan","repo_kind":"official","path":"datasets/action_util.py","file_url":"https://github.com/akshitac8/tfvaegan/blob/HEAD/datasets/action_util.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ac965f971d0020b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}