ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization

08/18/2022
by   Jiwon Kim, et al.
0

We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views of an image, weighted by a confidence of pseudo-label, dubbed ConMatch. While the latest semi-supervised learning methods use weakly- and strongly-augmented views of an image to define a directional consistency loss, how to define such direction for the consistency regularization between two strongly-augmented views remains unexplored. To account for this, we present novel confidence measures for pseudo-labels from strongly-augmented views by means of weakly-augmented view as an anchor in non-parametric and parametric approaches. Especially, in parametric approach, we present, for the first time, to learn the confidence of pseudo-label within the networks, which is learned with backbone model in an end-to-end manner. In addition, we also present a stage-wise training to boost the convergence of training. When incorporated in existing semi-supervised learners, ConMatch consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our ConMatch over the latest methods and provide extensive ablation studies. Code has been made publicly available at https://github.com/JiwonCocoder/ConMatch.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/21/2020

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Semi-supervised learning (SSL) provides an effective means of leveraging...
research
10/23/2022

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training

Self-training methods have been explored in recent years and have exhibi...
research
12/22/2021

Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images

This paper tackles the problem of semi-supervised learning when the set ...
research
03/30/2022

Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels

Establishing dense correspondences across semantically similar images re...
research
01/25/2022

AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning

Semi-supervised learning (SSL) has recently proven to be an effective pa...
research
08/13/2023

Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning

Semi-supervised learning is attracting blooming attention, due to its su...
research
03/18/2022

Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation

We propose a semi-supervised learning framework for monocular depth esti...

Please sign up or login with your details

Forgot password? Click here to reset