Multi-modal Self-Supervision from Generalized Data Transformations

The recent success of self-supervised learning can be largely attributed to content-preserving transformations, which can be used to easily induce invariances. While transformations generate positive sample pairs in contrastive loss training, most recent work focuses on developing new objective formulations, and pays relatively little attention to the transformations themselves... (read more)

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

Results from the Paper


 Ranked #1 on Action Recognition on UCF-101 (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Action Recognition UCF-101 GDT Top 1 Accuracy 95.2 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet