SemPPL: Predicting pseudo-labels for better contrastive representations

by   Matko Bošnjak, et al.

Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that combines labelled and unlabelled data to learn informative representations. Our method extends self-supervised contrastive learning – where representations are shaped by distinguishing whether two samples represent the same underlying datum (positives) or not (negatives) – with a novel approach to selecting positives. To enrich the set of positives, we leverage the few existing ground-truth labels to predict the missing ones through a k-nearest neighbours classifier by using the learned embeddings of the labelled data. We thus extend the set of positives with datapoints having the same pseudo-label and call these semantic positives. We jointly learn the representation and predict bootstrapped pseudo-labels. This creates a reinforcing cycle. Strong initial representations enable better pseudo-label predictions which then improve the selection of semantic positives and lead to even better representations. SemPPL outperforms competing semi-supervised methods setting new state-of-the-art performance of 68.5% and 76% top-1 accuracy when using a ResNet-50 and training on 1% and 10% of labels on ImageNet, respectively. Furthermore, when using selective kernels, SemPPL significantly outperforms previous state-of-the-art achieving 72.3% and 78.3% top-1 accuracy on ImageNet with 1% and 10% labels, respectively, which improves absolute +7.8% and +6.2% over previous work. SemPPL also exhibits state-of-the-art performance over larger ResNet models as well as strong robustness, out-of-distribution and transfer performance.


CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

Semi-supervised learning has been an effective paradigm for leveraging u...

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

This paper proposes a novel method of learning by predicting view assign...

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

We propose a three-stage training strategy called dual pseudo training (...

A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning

For an image query, unsupervised contrastive learning labels crops of th...

Data-Efficient Image Recognition with Contrastive Predictive Coding

Large scale deep learning excels when labeled images are abundant, yet d...

MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset

Deep learning has achieved great success in recent years with the aid of...

Active Refinement for Multi-Label Learning: A Pseudo-Label Approach

The goal of multi-label learning (MLL) is to associate a given instance ...

Please sign up or login with your details

Forgot password? Click here to reset