{"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/meta-learning-initializations-for-image-1","title":"Meta-Learning Initializations for Image Segmentation","arxiv_id":"1912.06290","date":"2019-12-13","proceeding":null,"authors":["Sean M. Hendryx","Andrew B. Leach","Paul D. Hein","Clayton T. Morrison"],"abstract":"We extend first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, present a novel neural network architecture built for fast learning which we call EfficientLab, and leverage a formal definition of the test error of meta-learning algorithms to decrease error on out of distribution tasks. We show state of the art results on the FSS-1000 dataset by meta-training EfficientLab with FOMAML and using Bayesian optimization to infer the optimal test-time adaptation routine hyperparameters. We also construct a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. On the FP-k dataset, we show that meta-learned initializations provide value for canonical few-shot image segmentation but their performance is quickly matched by conventional transfer learning with performance being equal beyond 10 labeled examples. Our code, meta-learned model, and the FP-k dataset are available at https://github.com/ml4ai/mliis .","url_abs":"https://arxiv.org/abs/1912.06290v4","url_pdf":"https://arxiv.org/pdf/1912.06290v4.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":"meta-learning-initializations-for-image-1","repo_url":"https://github.com/ml4ai/mliis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-fss-1000","task":"Few-Shot Semantic Segmentation","dataset":"FSS-1000","model":"EfficientLab","rank_in_archive_order":3,"of":3,"metrics":{"Mean IoU":"82.78"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.06290","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}