{"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/discriminative-k-shot-learning-using","title":"Discriminative k-shot learning using probabilistic models","arxiv_id":"1706.00326","date":"2017-06-01","proceeding":"ICLR 2018 1","authors":["Matthias Bauer","Mateo Rojas-Carulla","Jakub Bartłomiej Świątkowski","Bernhard Schölkopf","Richard E. Turner"],"abstract":"This paper introduces a probabilistic framework for k-shot image\nclassification. The goal is to generalise from an initial large-scale\nclassification task to a separate task comprising new classes and small numbers\nof examples. The new approach not only leverages the feature-based\nrepresentation learned by a neural network from the initial task\n(representational transfer), but also information about the classes (concept\ntransfer). The concept information is encapsulated in a probabilistic model for\nthe final layer weights of the neural network which acts as a prior for\nprobabilistic k-shot learning. We show that even a simple probabilistic model\nachieves state-of-the-art on a standard k-shot learning dataset by a large\nmargin. Moreover, it is able to accurately model uncertainty, leading to well\ncalibrated classifiers, and is easily extensible and flexible, unlike many\nrecent approaches to k-shot learning.","url_abs":"http://arxiv.org/abs/1706.00326v2","url_pdf":"http://arxiv.org/pdf/1706.00326v2.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"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"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-4","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (10-shot)","model":"ResNet-34 (Isotropic Gaussian)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"78.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.00326","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}