{"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/few-shot-adaptive-gaze-estimation","title":"Few-Shot Adaptive Gaze Estimation","arxiv_id":"1905.01941","date":"2019-05-06","proceeding":"ICCV 2019 10","authors":["Seonwook Park","Shalini De Mello","Pavlo Molchanov","Umar Iqbal","Otmar Hilliges","Jan Kautz"],"abstract":"Inter-personal anatomical differences limit the accuracy of person-independent gaze estimation networks. Yet there is a need to lower gaze errors further to enable applications requiring higher quality. Further gains can be achieved by personalizing gaze networks, ideally with few calibration samples. However, over-parameterized neural networks are not amenable to learning from few examples as they can quickly over-fit. We embrace these challenges and propose a novel framework for Few-shot Adaptive GaZE Estimation (FAZE) for learning person-specific gaze networks with very few (less than or equal to 9) calibration samples. FAZE learns a rotation-aware latent representation of gaze via a disentangling encoder-decoder architecture along with a highly adaptable gaze estimator trained using meta-learning. It is capable of adapting to any new person to yield significant performance gains with as few as 3 samples, yielding state-of-the-art performance of 3.18 degrees on GazeCapture, a 19% improvement over prior art. We open-source our code at https://github.com/NVlabs/few_shot_gaze","url_abs":"https://arxiv.org/abs/1905.01941v2","url_pdf":"https://arxiv.org/pdf/1905.01941v2.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":"few-shot-adaptive-gaze-estimation","repo_url":"https://github.com/NVlabs/few_shot_gaze","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"gaze-estimation","task_name":"Gaze Estimation"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gaze-estimation-on-mpii-gaze","task":"Gaze Estimation","dataset":"MPII Gaze","model":"FAZE","rank_in_archive_order":1,"of":6,"metrics":{"Angular Error":"3.14"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.01941","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}