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

04/01/2022
by   Renjie Xu, et al.
0

Few-Shot classification aims at solving problems that only a few samples are available in the training process. Due to the lack of samples, researchers generally employ a set of training tasks from other domains to assist the target task, where the distribution between assistant tasks and the target task is usually different. To reduce the distribution gap, several lines of methods have been proposed, such as data augmentation and domain alignment. However, one common drawback of these algorithms is that they ignore the similarity task selection before training. The fundamental problem is to push the auxiliary tasks close to the target task. In this paper, we propose a novel task selecting algorithm, named Optimal Transport Task Selecting (OTTS), to construct a training set by selecting similar tasks for Few-Shot learning. Specifically, the OTTS measures the task similarity by calculating the optimal transport distance and completes the model training via a self-supervised strategy. By utilizing the selected tasks with OTTS, the training process of Few-Shot learning become more stable and effective. Other proposed methods including data augmentation and domain alignment can be used in the meantime with OTTS. We conduct extensive experiments on a variety of datasets, including MiniImageNet, CIFAR, CUB, Cars, and Places, to evaluate the effectiveness of OTTS. Experimental results validate that our OTTS outperforms the typical baselines, i.e., MAML, matchingnet, protonet, by a large margin (averagely 1.72% accuracy improvement).

READ FULL TEXT

page 4

page 6

page 8

page 12

research
09/03/2021

Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition

The domain shift between the source and target domain is the main challe...
research
01/19/2021

Cross-domain few-shot learning with unlabelled data

Few shot learning aims to solve the data scarcity problem. If there is a...
research
04/16/2021

Pareto Self-Supervised Training for Few-Shot Learning

While few-shot learning (FSL) aims for rapid generalization to new conce...
research
10/20/2019

An Optimal Transport Framework for Zero-Shot Learning

We present an optimal transport (OT) framework for generalized zero-shot...
research
10/18/2021

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

Few-shot classification is a challenging problem due to the uncertainty ...
research
05/08/2022

PGADA: Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-Query Shift

Few-shot learning methods aim to embed the data to a low-dimensional emb...
research
02/24/2021

Enabling the Network to Surf the Internet

Few-shot learning is challenging due to the limited data and labels. Exi...

Please sign up or login with your details

Forgot password? Click here to reset