Pnnclr: Stochastic Pseudo Neighborhoods For Contrastive Learning Based Unsupervised Representation Learning Problems

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. Eva

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keybiswas2023pnnclr

Related papers

• With A Little Help From My Friends: Nearest-neighbor Contrastive Learning Of Visual Representations (2021)18.76
• Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35
• Constrained Mean Shift For Representation Learning (2021)0.00
• Nearest-neighbor Inter-intra Contrastive Learning From Unlabeled Videos (2023)0.00
• Neural Nearest Neighbors Networks (2018)0.00
• Representation Learning By Reconstructing Neighborhoods (2018)0.00
• Revisiting Contrastive Methods For Unsupervised Learning Of Visual Representations (2021)3.91
• Transformer-based Clipped Contrastive Quantization Learning For Unsupervised Image Retrieval (2024)5.84