Papers › IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised...

IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation

18 Mar 2024IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024 3archive 2025-07-28

Sonal Kumar; Anirudh Phukan, Arijit Sur

Self-supervised learning with a contrastive batch approach has become a powerful tool for representation learning in computer vision. The performance of downstream tasks is proportional to the quality of visual features learned while self-supervised pre-training. The existing contrastive batch approaches heavily depend on data augmentation to learn latent information from unlabelled datasets. We argue that introducing the dataset’s intra-class variation in a contrastive batch approach improves visual representation quality further. In this paper, we propose a novel self-supervised learning approach named Iterative Pseudo-supervised Contrastive Learning (IPCL), which utilizes a balanced combination of image augmentations and pseudo-class information to improve the visual representation iteratively. Experimental results illustrate that our proposed method surpasses the baseline self-supervised method with the batch contrastive approach. It improves the visual representation quality over multiple datasets, leading to better performance on the downstream unsupervised image classification task.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningData AugmentationImage ClassificationImage ClusteringRepresentation LearningSelf-Supervised Image ClassificationSelf-Supervised LearningUnsupervised Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Contrastive Learning CIFAR-10 IPCL (ResNet18) Accuracy (Top-1) 84.77 #1 of 1 Archive leaderboard report
Contrastive Learning STL-10 IPCL (ResNet18) Accuracy (Top-1) 85.55 #1 of 1 Archive leaderboard report
Unsupervised Image Classification CIFAR-10 IPCL (ResNet18) Accuracy 88.81 #9 of 9 Archive leaderboard report
Unsupervised Image Classification STL-10 IPCL (ResNet18) Accuracy 80.91 #9 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections