2022/11/02 by Yifei Zhang, Zhang, Yifei, Chang Liu +9 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Text and Document Classification Technologies
paper · pdf · doi:10.48550/arxiv.2211.01796
openalex publication_date 2022/11/02 · openalex created_date 2022/11/09 · openalex updated_date 2026/07/28
Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined binary self-supervision. However, vanilla CSL is inadequate in modeling sophisticated instance relations, limiting the learned model to retain fine semantic structure. On the one hand, samples with the same semantic category are inevitably pushed away as negatives. On the other hand, differences among samples cannot be captured. In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i.e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion. Specifically, we align similarity distributions calculated between the positive anchor views and the negatives at the global level to exploit diverse similarity relations among instances. Local-level interpolation consistency between the pixel space and the feature space is applied to quantitatively model the feature differences of samples with distinct apparent similarities. Through explicitly instance relation modeling, our ReCo avoids irrationally pushing away semantically identical samples and carves a well-structured feature space. Extensive experiments conducted on commonly used benchmarks justify that our ReCo consistently gains remarkable performance improvements.