Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning

10/18/2021
by   Yuqing Hu, et al.
0

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously solved task, what is often achieved by using a pretrained feature extractor. Following this vein, in this paper we propose a novel transfer-based method which aims at processing the feature vectors so that they become closer to Gaussian-like distributions, resulting in increased accuracy. In the case of transductive few-shot learning where unlabelled test samples are available during training, we also introduce an optimal-transport inspired algorithm to boost even further the achieved performance. Using standardized vision benchmarks, we show the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/06/2020

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

Few-shot classification is a challenging problem due to the uncertainty ...
research
01/16/2023

Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approach

The field of visual few-shot classification aims at transferring the sta...
research
09/18/2022

Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification

Transductive Few-Shot learning has gained increased attention nowadays c...
research
08/05/2022

Convolutional Ensembling based Few-Shot Defect Detection Technique

Over the past few years, there has been a significant improvement in the...
research
01/27/2020

Exploiting Unsupervised Inputs for Accurate Few-Shot Classification

In few-shot classification, the aim is to learn models able to discrimin...
research
04/15/2021

Embedding Adaptation is Still Needed for Few-Shot Learning

Constructing new and more challenging tasksets is a fruitful methodology...
research
04/01/2022

Selecting task with optimal transport self-supervised learning for few-shot classification

Few-Shot classification aims at solving problems that only a few samples...

Please sign up or login with your details

Forgot password? Click here to reset