Unsupervised Natural Image Patch Learning

Abstract

Learning a metric of natural image patches is an important tool for analyzing images. An efficient means is to train a deep network to map an image patch to a vector space, in which the Euclidean distance reflects patch similarity. Previous attempts learned such an embedding in a supervised manner, requiring the availability of many annotated images. In this paper, we present an unsupervised embedding of natural image patches, avoiding the need for annotated images. The key idea is that the similarity of two patches can be learned from the prevalence of their spatial proximity in natural images. Clearly, relying on this simple principle, many spatially nearby pairs are outliers, however, as we show, the outliers do not harm the convergence of the metric learning. We show that our unsupervised embedding approach is more effective than a supervised one or one that uses deep patch representations. Moreover, we show that it naturally leads itself to an efficient self-supervised domain adap

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keydanon2018unsupervised

Related papers

• Convolutional Patch Representations For Image Retrieval: An Unsupervised Approach (2016)12.47
• Self-taught Metric Learning Without Labels (2022)9.41
• A Probabilistic Approach For Learning Embeddings Without Supervision (2019)0.00
• Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding (2020)2.26
• Why And How: Knowledge-guided Learning For Cross-spectral Image Patch Matching (2024)3.31
• Augnet: End-to-end Unsupervised Visual Representation Learning With Image Augmentation (2021)3.96
• Semi-supervised Deep Learning By Metric Embedding (2016)0.00
• Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66