Exploring Instance Relations for Unsupervised Feature Embedding

Abstract

Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations. In this paper, we explore instance relations including intra-instance multi-view relation and inter-instance interpolation relation for unsupervised feature embedding. Specifically, we embed intra-instance multi-view relation by aligning the distribution of the distance between an instance's different augmented samples and negative samples. We explore inter-instance interpolation relation by transferring the ratio of information for image sample interpolation from pixel space to feature embedding space. The proposed approach, referred to as EIR, is simple-yet-effective and can be easily inserted into existing view-invariant contrastive learning based methods. Experiments conducted on public benchmarks for image classification and retrieval report state-of-the-art or comparable performance.

7 pages, 6 figures

References in corpus (2)

• Unsupervised Embedding Learning via Invariant and Spreading Instance Feature
• Local Aggregation for Unsupervised Learning of Visual Embeddings

Cited by in corpus (4)

• MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification
• Dense Semantic Contrast for Self-Supervised Visual Representation Learning
• Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
• PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition