Deep Unsupervised Similarity Learning Using Partially Ordered Sets

Abstract

Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information that relates different tuples or triplets to each other. To overcome this problem, we use local estimates of reliable (dis-)similarities to initially group samples into compact surrogate classes and use local partial orders of samples to classes to link classes to each other. Similarity learning is then formulated as a partial ordering task with soft correspondences of all samples to classes. Adopting a strategy of self-supervision, a CNN is trained to optimally represent samples in a mutually consistent manner while updating the classes. The similarity learning and grouping procedure are in

Stats

• citations19
• S2 citations—
• github stars0
• HF likes0
• heat score9.76
• arxiv keybautista2017deep

Related papers

• Improving Spatiotemporal Self-supervision By Deep Reinforcement Learning (2018)13.50
• Digging Into Self-supervised Learning Of Feature Descriptors (2021)7.16
• SUVR: A Search-based Approach To Unsupervised Visual Representation Learning (2023)3.58
• Unsupervised Part Learning For Visual Recognition (2017)8.82
• PADS: Policy-adapted Sampling For Visual Similarity Learning (2020)15.46
• Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66
• Self-supervised Video Similarity Learning (2023)13.04
• Revisiting Contrastive Methods For Unsupervised Learning Of Visual Representations (2021)3.91