ActiveMatch: End-to-end Semi-supervised Active Representation Learning

10/06/2021
by   Xinkai Yuan, et al.
0

Semi-supervised learning (SSL) is an efficient framework that can train models with both labeled and unlabeled data. However, constrained by the limited number of labels, the learned representations of SSL are ambiguous and not distinguishable for inter-class samples. Moreover, the performance of SSL is also largely dependent on the model initialization. To deal with the drawbacks of SSL, in this paper, we propose a novel end-to-end representation learning method, namely ActiveMatch, which combines SSL with contrastive learning and active learning to fully leverage the limited labels. Starting from a small amount of labeled data with unsupervised contrastive learning as a warm-up, ActiveMatch then combines SSL and supervised contrastive learning, and actively selects the most representative samples for labeling during the training, resulting in better representations towards the classification. Compared with MixMatch and FixMatch, we show that ActiveMatch achieves the state-of-the-art performance, with 89.24 accuracy on CIFAR-10 with 100 collected labels, and 92.20 accuracy with 200 collected labels.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/23/2020

CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

Semi-supervised learning has been an effective paradigm for leveraging u...
research
06/05/2022

Semi-Supervised Learning for Mars Imagery Classification and Segmentation

With the progress of Mars exploration, numerous Mars image data are coll...
research
10/14/2022

Spatiotemporal Classification with limited labels using Constrained Clustering for large datasets

Creating separable representations via representation learning and clust...
research
08/25/2022

Supervised Contrastive Learning for Affect Modelling

Affect modeling is viewed, traditionally, as the process of mapping meas...
research
11/11/2021

Semantic-aware Representation Learning Via Probability Contrastive Loss

Recent feature contrastive learning (FCL) has shown promising performanc...
research
11/28/2022

Deep Semi-supervised Learning with Double-Contrast of Features and Semantics

In recent years, the field of intelligent transportation systems (ITS) h...
research
02/24/2022

Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning

Semi-supervised learning (SSL) has long been proved to be an effective t...

Please sign up or login with your details

Forgot password? Click here to reset