Enhancing Few-Shot Image Classification with Unlabelled Examples

2020-06-17 · Peyman Bateni, Jarred Barber, Jan-Willem van de Meent, Frank Wood

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 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 state of the art performance on the Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks. All trained models and code have been made publicly available at github.com/plai-group/simple-cnaps.

📄 PDF Abstract BibTeX arXiv:2006.12245

Code (2)

plai-group/simple-cnaps 공식 구현 tf

peymanbateni/simple-cnaps pytorch

Tasks

ClassificationClusteringFew-Shot Image Classification Few-Shot Learning General Classification image-classification Image Classification Meta-Learning Object Recognition

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Improving Few-Shot Visual Classification with Unlabelled Examples

2020-09-28 · Peyman Bateni, Jarred Barber, Jan-Willem van de Meent, Frank Wood

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 p…

Classification Clustering Few-Shot Image Classification Few-Shot Learning+3

On the Importance of Distractors for Few-Shot Classification

2021-09-20 · ICCV 2021 10 · Rajshekhar Das, Yu-Xiong Wang, JoséM. F. Moura

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…

Classification Contrastive Learning

Negative Confidence-Aware Weakly Supervised Binary Classification for Effective Review Helpfulness Classification

2020-08-14 · Xi Wang, Iadh Ounis, Craig Macdonald

The incompleteness of positive labels and the presence of many unlabelled instances are common problems in binary classification applications such as in review helpfulness classification. Various studies from the classif…

Binary Classification Classification General Classification

Memory Matching Networks for One-Shot Image Recognition

2018-04-23 · CVPR 2018 6 · Qi Cai, Yingwei Pan, Ting Yao, Chenggang Yan 외

In this paper, we introduce the new ideas of augmenting Convolutional Neural Networks (CNNs) with Memory and learning to learn the network parameters for the unlabelled images on the fly in one-shot learning. Specificall…

One-Shot Learning Philosophy

Automatically Discovering and Learning New Visual Categories with Ranking Statistics

2020-02-13 · ICLR 2020 1 · Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi 외

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…

Clustering General Classification Self-Supervised Learning