SUVR: A Search-based Approach To Unsupervised Visual Representation Learning

Abstract

Unsupervised learning has grown in popularity because of the difficulty of collecting annotated data and the development of modern frameworks that allow us to learn from unlabeled data. Existing studies, however, either disregard variations at different levels of similarity or only consider negative samples from one batch. We argue that image pairs should have varying degrees of similarity, and the negative samples should be allowed to be drawn from the entire dataset. In this work, we propose Search-based Unsupervised Visual Representation Learning (SUVR) to learn better image representations in an unsupervised manner. We first construct a graph from the image dataset by the similarity between images, and adopt the concept of graph traversal to explore positive samples. In the meantime, we make sure that negative samples can be drawn from the full dataset. Quantitative experiments on five benchmark image classification datasets demonstrate that SUVR can significantly outperform strong

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyxu2023suvr

Related papers

• Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35
• VISER: Visual Self-regularization (2018)0.00
• Towards Unsupervised Sketch-based Image Retrieval (2021)0.00
• Revisiting Contrastive Methods For Unsupervised Learning Of Visual Representations (2021)3.91
• Attributable Visual Similarity Learning (2022)11.68
• Univse: Robust Visual Semantic Embeddings Via Structured Semantic Representations (2019)0.00
• Deep Unsupervised Similarity Learning Using Partially Ordered Sets (2017)9.76
• Feature Representation Learning For Unsupervised Cross-domain Image Retrieval (2022)11.46