{"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/rapid-adaptation-with-conditionally-shifted","title":"Rapid Adaptation with Conditionally Shifted Neurons","arxiv_id":"1712.09926","date":"2017-12-28","proceeding":"ICML 2018 7","authors":["Tsendsuren Munkhdalai","Xingdi Yuan","Soroush Mehri","Adam Trischler"],"abstract":"We describe a mechanism by which artificial neural networks can learn rapid\nadaptation - the ability to adapt on the fly, with little data, to new tasks -\nthat we call conditionally shifted neurons. We apply this mechanism in the\nframework of metalearning, where the aim is to replicate some of the\nflexibility of human learning in machines. Conditionally shifted neurons modify\ntheir activation values with task-specific shifts retrieved from a memory\nmodule, which is populated rapidly based on limited task experience. On\nmetalearning benchmarks from the vision and language domains, models augmented\nwith conditionally shifted neurons achieve state-of-the-art results.","url_abs":"http://arxiv.org/abs/1712.09926v3","url_pdf":"http://arxiv.org/pdf/1712.09926v3.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":"few-shot-image-classification","task_name":"Few-Shot Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"adaResNet (DF)","rank_in_archive_order":80,"of":105,"metrics":{"Accuracy":"56.88"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"adaResNet (DF)","rank_in_archive_order":76,"of":95,"metrics":{"Accuracy":"71.94"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-1","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 1-Shot, 20-way","model":"adaCNN (DF)","rank_in_archive_order":11,"of":20,"metrics":{"Accuracy":"96.12%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 1-Shot, 5-way","model":"adaCNN (DF)","rank_in_archive_order":12,"of":17,"metrics":{"Accuracy":"98.42"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-1","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 5-Shot, 20-way","model":"adaCNN (DF)","rank_in_archive_order":14,"of":19,"metrics":{"Accuracy":"98.43%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 5-Shot, 5-way","model":"adaCNN (DF)","rank_in_archive_order":15,"of":16,"metrics":{"Accuracy":"99.37"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.09926","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}