{"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/synthetic-sample-selection-for-generalized","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","arxiv_id":"2304.02846","date":"2023-04-06","proceeding":null,"authors":["Shreyank N Gowda"],"abstract":"Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training. Despite the significant progress achieved by generative techniques in converting traditional GZSL to fully supervised learning, they tend to generate a large number of synthetic features that are often redundant, thereby increasing training time and decreasing accuracy. To address this issue, this paper proposes a novel approach for synthetic feature selection using reinforcement learning. In particular, we propose a transformer-based selector that is trained through proximal policy optimization (PPO) to select synthetic features based on the validation classification accuracy of the seen classes, which serves as a reward. The proposed method is model-agnostic and data-agnostic, making it applicable to both images and videos and versatile for diverse applications. Our experimental results demonstrate the superiority of our approach over existing feature-generating methods, yielding improved overall performance on multiple benchmarks.","url_abs":"https://arxiv.org/abs/2304.02846v1","url_pdf":"https://arxiv.org/pdf/2304.02846v1.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":[],"tasks":[{"task_slug":"generalized-zero-shot-learning","task_name":"Generalized Zero-Shot Learning"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"feature-selection","method_name":"Feature Selection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-zero-shot-learning-on-cub-200","task":"Generalized Zero-Shot Learning","dataset":"CUB-200-2011","model":"SPOT (DAA)","rank_in_archive_order":2,"of":3,"metrics":{"Harmonic mean":"67.0"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-oxford-102-1","task":"Generalized Zero-Shot Learning","dataset":"Oxford 102 Flower","model":"SPOT (FREE)","rank_in_archive_order":1,"of":2,"metrics":{"Harmonic mean":"75.9"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-sun","task":"Generalized Zero-Shot Learning","dataset":"SUN Attribute","model":"SPOT (CMC-GAN)","rank_in_archive_order":2,"of":9,"metrics":{"Harmonic mean":"46.4"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-hmdb51","task":"Zero-Shot Action Recognition","dataset":"HMDB51","model":"SPOT","rank_in_archive_order":18,"of":29,"metrics":{"Top-1 Accuracy":"35.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-olympics","task":"Zero-Shot Action Recognition","dataset":"Olympics","model":"SPOT","rank_in_archive_order":1,"of":9,"metrics":{"Top-1 Accuracy":"68.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"SPOT","rank_in_archive_order":22,"of":35,"metrics":{"Top-1 Accuracy":"40.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-cub-200-2011","task":"Zero-Shot Learning","dataset":"CUB-200-2011","model":"SPOT","rank_in_archive_order":7,"of":14,"metrics":{"average top-1 classification accuracy":"62.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-oxford-102-flower","task":"Zero-Shot Learning","dataset":"Oxford 102 Flower","model":"SPOT","rank_in_archive_order":1,"of":2,"metrics":{"average top-1 classification accuracy":"71.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-learning-on-sun-attribute","task":"Zero-Shot Learning","dataset":"SUN Attribute","model":"SPOT (VAEGAN)","rank_in_archive_order":2,"of":9,"metrics":{"average top-1 classification accuracy":"66.04"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2304.02846","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}