{"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/zero-shot-logit-adjustment","title":"Zero-Shot Logit Adjustment","arxiv_id":"2204.11822","date":"2022-04-25","proceeding":null,"authors":["Dubing Chen","Yuming Shen","Haofeng Zhang","Philip H. S. Torr"],"abstract":"Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses challenges in recognizing novel classes in the test phase. The development of generative models enables current GZSL techniques to probe further into the semantic-visual link, culminating in a two-stage form that includes a generator and a classifier. However, existing generation-based methods focus on enhancing the generator's effect while neglecting the improvement of the classifier. In this paper, we first analyze of two properties of the generated pseudo unseen samples: bias and homogeneity. Then, we perform variational Bayesian inference to back-derive the evaluation metrics, which reflects the balance of the seen and unseen classes. As a consequence of our derivation, the aforementioned two properties are incorporated into the classifier training as seen-unseen priors via logit adjustment. The Zero-Shot Logit Adjustment further puts semantic-based classifiers into effect in generation-based GZSL. Our experiments demonstrate that the proposed technique achieves state-of-the-art when combined with the basic generator, and it can improve various generative Zero-Shot Learning frameworks. Our codes are available on https://github.com/cdb342/IJCAI-2022-ZLA.","url_abs":"https://arxiv.org/abs/2204.11822v4","url_pdf":"https://arxiv.org/pdf/2204.11822v4.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":"zero-shot-logit-adjustment","repo_url":"https://github.com/cdb342/ijcai-2022-zla","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"generalized-zero-shot-learning","task_name":"Generalized Zero-Shot Learning"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-zero-shot-learning-on-awa2","task":"Generalized Zero-Shot Learning","dataset":"AwA2","model":"WGAN+ZLAP","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy Seen":"82.2","Accuracy Unseen":"65.4","H":"72.8"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-caltech","task":"Generalized Zero-Shot Learning","dataset":"Caltech-UCSD Birds 200 - 2011","model":"WGAN+ZLAP","rank_in_archive_order":1,"of":1,"metrics":{"H":"68.7"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-sun","task":"Generalized Zero-Shot Learning","dataset":"SUN Attribute","model":"WGAN+ZLAP","rank_in_archive_order":9,"of":9,"metrics":{"H":"43.2"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-zero-shot-learning-on-apy","task":"Generalized Zero-Shot Learning","dataset":"aPY","model":"WGAN+ZLAP","rank_in_archive_order":1,"of":1,"metrics":{"H":"46"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.11822","atlas_url":"https://app.syntology.ai/?focus=2204.11822","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}