Improving Few-Shot Visual Classification with Unlabelled Examples
We propose a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering procedure with a modified state of the art neural adaptive feature extractor to achieve improved test-time classification accuracy using unlabelled data. We evaluate our method on transductive few-shot learning tasks, in which the goal is to jointly predict labels for query (test) examples given a set of support (training) examples. We achieve new state of the art performance on the Meta-Dataset and the mini-ImageNet and tiered-ImageNet benchmarks.
Code (2)
Tasks
ClassificationClusteringFew-Shot Image ClassificationFew-Shot Learningimage-classificationImage ClassificationMeta-LearningSimilar Papers 제목 키워드 기반
Enhancing Few-Shot Image Classification with Unlabelled Examples
We develop a transductive meta-learning method that uses unlabelled instances to improve few-shot image classification performance. Our approach combines a regularized Mahalanobis-distance-based soft k-means clustering p…
ClassificationClusteringFew-Shot Image ClassificationFew-Shot Learning+5On the Importance of Distractors for Few-Shot Classification
Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classification involves a prior model trained on…
ClassificationContrastive LearningVisual Transformer for Task-aware Active Learning
Pool-based sampling in active learning (AL) represents a key framework for an-notating informative data when dealing with deep learning models. In this paper, we present a novel pipeline for pool-based Active Learning. U…
Active LearningVisually grounded few-shot word acquisition with fewer shots
We propose a visually grounded speech model that acquires new words and their visual depictions from just a few word-image example pairs. Given a set of test images and a spoken query, we ask the model which image depict…
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. This setting is similar to semi-supervised learning, but significantly harder because there are no label…
ClusteringGeneral ClassificationSelf-Supervised Learning