Deep Unsupervised Similarity Learning Using Partially Ordered Sets

By Miguel Angel Bautista, Artsiom Sanakoyeu, Björn Ommer. 2017

28 citations recorded by the source corpus.

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 integrated in a single model and optimized jointly. The proposed unsupervised approach shows competitive performance on detailed pose estimation and object classification.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Invariant Information Clustering for Unsupervised Image Classification and Segmentation (2018, methodology): “Agglomerative clustering [2] and partially ordered sets [1] of HOG features [13] have been used to group images, and exemplars [18] define a group as a set of random transformations applied to a single image.”
Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition (2018, methodology): “Other unsupervised representation learning approaches include exemplar CNNs [11], CliqueCNNs [4] and unsupervised similarity learning by clustering [3].”
Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks (2019, background): “The recent trend in the Computer Vision community is unsupervised or self-supervised learning [10, 34, 36, 25, 2, 1, 41, 5, 20, 29] which can make use of an abundant unlabeled visual data available on the internet and avoid costly manual annotations.”
A Variational U-Net for Conditional Appearance and Shape Generation (2018, result): “In contrast to our generative approach, [4, 3] have pursued unsupervised learning of human posture similarity for retrieval in still images and [25, 5] in videos.”
Mining on Manifolds: Metric Learning Without Labels (2018, methodology): “The approaches to obtain relevant training data range from further human supervision [3, 36] to instance clustering [44, 32, 5], exploiting the temporal dimension in video [64, 65], predicting the spatial layout of image patches [11], or using existing computer vision pipelines to match unstructured”
Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning (2018, background): “Without any annotations, self-supervision based on surrogate tasks, for which the target value can be obtained automatically, is commonly pursued [32, 28, 17, 3, 34, 10, 31, 35, 30, 39, 27, 9, 18, 45].”