pNNCLR: Stochastic Pseudo Neighborhoods for Contrastive Learning based Unsupervised Representation Learning Problems
Preprint
Abstract
Nearest neighbor (NN) sampling provides more semantic variations than pre-defined transformations for self-supervised learning (SSL) based image recognition problems. However, its performance is restricted by the quality of the support set, which holds positive samples for the contrastive loss. In this work, we show that the quality of the support set plays a crucial role in any nearest neighbor based method for SSL. We then provide a refined baseline (pNNCLR) to the nearest neighbor based SSL approach (NNCLR). To this end, we introduce pseudo nearest neighbors (pNN) to control the quality of the support set, wherein, rather than sampling the nearest neighbors, we sample in the vicinity of hard nearest neighbors by varying the magnitude of the resultant vector and employing a stochastic sampling strategy to improve the performance. Additionally, to stabilize the effects of uncertainty in NN-based learning, we employ a smooth-weight-update approach for training the proposed network. Evaluation of the proposed method on multiple public image recognition and medical image recognition datasets shows that it performs up to 8 percent better than the baseline nearest neighbor method, and is comparable to other previously proposed SSL methods.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Subclass-balancing Contrastive Learning for Long-tailed Recognition2023
- Summary of ChatGPT-Related research and perspective towards the future of large language modelsMeta-Radiology, 2023
- Context Autoencoder for Self-supervised Representation LearningInternational Journal of Computer Vision, 2023
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- Application of transfer learning and ensemble learning in image-level classification for breast histopathologyIntelligent Medicine, 2022