A Framework For Contrastive Self-Supervised Learning And Designing A New Approach

Contrastive self-supervised learning (CSL) is an approach to learn useful representations by solving a pretext task that selects and compares anchor, negative and positive (APN) features from an unlabeled dataset. We present a conceptual framework that characterizes CSL approaches in five aspects (1) data augmentation pipeline, (2) encoder selection, (3) representation extraction, (4) similarity measure, and (5) loss function... (read more)

PDF Abstract ICLR 2021 PDF (under review) ICLR 2021 Abstract (under review)

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification STL-10 Simulated Fixations Percentage correct 61 # 89
Image Classification STL-10 YADIM Percentage correct 92.15 # 26
Image Classification STL-10 CPC† Percentage correct 78.36 # 59
Image Classification STL-10 AMDIM Percentage correct 93.80 # 22

Methods used in the Paper