{"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/tafe-net-task-aware-feature-embeddings-for-1","title":"TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning","arxiv_id":"1904.05967","date":"2019-04-11","proceeding":"CVPR 2019 6","authors":["Xin Wang","Fisher Yu","Ruth Wang","Trevor Darrell","Joseph E. Gonzalez"],"abstract":"Learning good feature embeddings for images often requires substantial\ntraining data. As a consequence, in settings where training data is limited\n(e.g., few-shot and zero-shot learning), we are typically forced to use a\ngeneric feature embedding across various tasks. Ideally, we want to construct\nfeature embeddings that are tuned for the given task. In this work, we propose\nTask-Aware Feature Embedding Networks (TAFE-Nets) to learn how to adapt the\nimage representation to a new task in a meta learning fashion. Our network is\ncomposed of a meta learner and a prediction network. Based on a task input, the\nmeta learner generates parameters for the feature layers in the prediction\nnetwork so that the feature embedding can be accurately adjusted for that task.\nWe show that TAFE-Net is highly effective in generalizing to new tasks or\nconcepts and evaluate the TAFE-Net on a range of benchmarks in zero-shot and\nfew-shot learning. Our model matches or exceeds the state-of-the-art on all\ntasks. In particular, our approach improves the prediction accuracy of unseen\nattribute-object pairs by 4 to 15 points on the challenging visual\nattribute-object composition task.","url_abs":"http://arxiv.org/abs/1904.05967v1","url_pdf":"http://arxiv.org/pdf/1904.05967v1.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":"tafe-net-task-aware-feature-embeddings-for-1","repo_url":"https://github.com/ucbdrive/tafe-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-awa1-0-shot","task":"Few-Shot Image Classification","dataset":"AWA1 - 0-Shot","model":"TAFE-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-awa2-0-shot","task":"Few-Shot Image Classification","dataset":"AWA2 - 0-Shot","model":"TAFE-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-0","task":"Few-Shot Image Classification","dataset":"CUB-200 - 0-Shot Learning","model":"TAFE-Net","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"56.9%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-sun-0-shot","task":"Few-Shot Image Classification","dataset":"SUN - 0-Shot","model":"TAFE-Net","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"60.9%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-apy-0-shot","task":"Few-Shot Image Classification","dataset":"aPY - 0-Shot","model":"TAFE-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"42.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.05967","atlas_url":"https://app.syntology.ai/?focus=1904.05967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05967"}},"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/ucbdrive/tafe-net","reach":null}],"summary":{"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"7e1973afe2913297","entry":"weighted_mse_loss","repo":"ucbdrive/tafe-net","repo_kind":"official","path":"compositional-zs/train_compose.py","file_url":"https://github.com/ucbdrive/tafe-net/blob/HEAD/compositional-zs/train_compose.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e1973afe2913297"}},{"code_sha256_prefix":"37fcef4cd9c4bcf0","entry":"validate","repo":"ucbdrive/tafe-net","repo_kind":"official","path":"compositional-zs/train_compose.py","file_url":"https://github.com/ucbdrive/tafe-net/blob/HEAD/compositional-zs/train_compose.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37fcef4cd9c4bcf0"}},{"code_sha256_prefix":"5bcda5b86b675fe9","entry":"validate","repo":"ucbdrive/tafe-net","repo_kind":"official","path":"zero-shot/train_zsl.py","file_url":"https://github.com/ucbdrive/tafe-net/blob/HEAD/zero-shot/train_zsl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5bcda5b86b675fe9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}