Unsupervised Deep Learning by Neighbourhood Discovery

By Jiabo Huang, Qi Dong, Shaogang Gong, Xiatian Zhu. 2019

162 citations recorded by the source corpus.

Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive training data annotations, limiting significantly their deployment and scalability in many application scenarios. In this work, we introduce a generic unsupervised deep learning approach to training deep models without the need for any manual label supervision. Specifically, we progressively discover sample anchored/centred neighbourhoods to reason and learn the underlying class decision boundaries iteratively and accumulatively. Every single neighbourhood is specially formulated so that all the member samples can share the same unseen class labels at high probability for facilitating the extraction of class discriminative feature representations during training. Experiments on image classification show the performance advantages of the proposed method over the state-of-the-art unsupervised learning models on six benchmarks including both coarse-grained and fine-grained object image categorisation.

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

Emerging Properties in Self-Supervised Vision Transformers (2021, background): “Several variants allow automatic grouping of instances in the form of clustering [2, 8, 9, 36, 42, 74, 80, 85].”
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (2020, neutral): “Our work is also related to clustering-based methods [2, 3, 6, 7, 17, 25, 50, 53, 54, 59].”
Self-labelling via simultaneous clustering and representation learning (2019, methodology): “We ﬁnd that the proposed method consistently outperforms the previous state of the art by around 2% across these datasets, even though AND is based on explicitly learning local neighbourhoods.”
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning (2021, methodology): “Instead of viewing each sample as its own class, clustering-based methods [3, 46, 44, 27, 51, 6, 1, 45, 18, 5, 7] regroup them into clusters based on some similarity measure.”
Unsupervised Contrastive Learning of Sound Event Representations (2020, methodology): “The prediction for every patch is, then, obtained by majority voting rule across the k neighbouring labels, where k = 200 as in [28, 29].”
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations (2021, background): “Methods that use prototypes/clusters [1, 2, 5, 6, 7, 23, 33, 53, 56, 57, 58, 60] also attempt to learn features by associating multiple samples with the same cluster.”
Learning To Classify Images Without Labels (2020, methodology): “In general, methods that rely on the initial feature representations of the network are sensitive to initialization [6,52,4,5,22,17,54], or prone to degenerate solutions [4,5], thus requiring special mechanisms (e.”
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, background): “These visual variations can be intra-instance variations such as different views of the same instance [125], [126], [127], [128], [129], or inter-instance variations between neighbor instances [130], [131] or across a group of instances [132], [133], [134].”
Unsupervised Image Classification for Deep Representation Learning (2020, unknown): “5 AND [20] 15.”
Understanding the Behaviour of Contrastive Loss (2020, background): “contents to learn instance-invariant representations, such as nearest neighbours discovery [14], local aggregation [37], invariance propagation [30], etc.”
Context Autoencoder for Self-supervised Representation Learning (2022, unknown): “Self-supervised representation learning has been widely studied in computer vision (Dosovitskiy et al., 2014; 2015; Doersch et al., 2015; Xie et al., 2016; Yang et al., 2016; van den Oord et al., 2018; Caron et al., 2018; Asano et al., 2019; Caron et al., 2019; Huang et al., 2019; Zhuang et al., 201”