QK Iteration: A Self-supervised Representation Learning Algorithm For Image Similarity

Abstract

Self-supervised representation learning is a fundamental problem in computer vision with many useful applications (e.g., image search, instance level recognition, copy detection). In this paper we present a new contrastive self-supervised representation learning algorithm in the context of Copy Detection in the 2021 Image Similarity Challenge hosted by Facebook AI Research. Previous work in contrastive self-supervised learning has identified the importance of being able to optimize representations while ``pushing'' against a large number of negative examples. Representative previous solutions either use large batches enabled by modern distributed training systems or maintain queues or memory banks holding recently evaluated representations while relaxing some consistency properties. We approach this problem from a new angle: We directly learn a query model and a key model jointly and push representations against a very large number (e.g., 1 million) of negative representations in each

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywu2021qk

Related papers

• Revisiting Contrastive Methods For Unsupervised Learning Of Visual Representations (2021)3.91
• 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
• Robust Cross-modal Representation Learning With Progressive Self-distillation (2022)12.33
• Self-supervised Video Representation Learning With Cross-stream Prototypical Contrasting (2021)8.82
• SUVR: A Search-based Approach To Unsupervised Visual Representation Learning (2023)3.58
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework (2020)18.58
• Cycle-contrast For Self-supervised Video Representation Learning (2020)0.00