# Learning Discrete Representations via Information Maximizing Self-Augmented Training

arXiv: https://arxiv.org/abs/1702.08720 · HTML: https://mlsanity.com/paper/1702.08720/

## Key facts

- Cited by 149 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2017.

## Built on by (most cited first, 30 of 149)

- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning](https://mlsanity.com/paper/2110.04361/) (2021)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes](https://mlsanity.com/paper/2207.11707/) (2022)
- [Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation](https://mlsanity.com/paper/2106.00131/) (2021)
- [Twin Contrastive Learning for Online Clustering](https://mlsanity.com/paper/2210.11680/) (2022)
- [ReconBoost: Boosting Can Achieve Modality Reconcilement](https://mlsanity.com/paper/2405.09321/) (2024)
- [The Hidden Uniform Cluster Prior in Self-Supervised Learning](https://mlsanity.com/paper/2210.07277/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [DINE: Domain Adaptation from Single and Multiple Black-box Predictors](https://mlsanity.com/paper/2104.01539/) (2021)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering](https://mlsanity.com/paper/2105.01899/) (2021)
- [Consistency Regularization for Cross-Lingual Fine-Tuning](https://mlsanity.com/paper/2106.08226/) (2021)
- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Variational Positive-incentive Noise: How Noise Benefits Models](https://mlsanity.com/paper/2306.07651/) (2023)
- [Image Clustering with External Guidance](https://mlsanity.com/paper/2310.11989/) (2023)
- [Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.02899/) (2024)
- [Transformer-Based Source-Free Domain Adaptation](https://mlsanity.com/paper/2105.14138/) (2021)
- [Multi-Facet Clustering Variational Autoencoders](https://mlsanity.com/paper/2106.05241/) (2021)
- [RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2309.15082/) (2023)
- [AVA-AVD: Audio-Visual Speaker Diarization in the Wild](https://mlsanity.com/paper/2111.14448/) (2021)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [ClusT3: Information Invariant Test-Time Training](https://mlsanity.com/paper/2310.12345/) (2023)
- [Pareto Domain Adaptation](https://mlsanity.com/paper/2112.04137/) (2021)
- [A Differential Entropy Estimator for Training Neural Networks](https://mlsanity.com/paper/2202.06618/) (2022)
- [ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery](https://mlsanity.com/paper/2504.03755/) (2025)

## Abstract (arXiv)

Learning discrete representations of data is a central machine learning task because of the compactness of the representations and ease of interpretation. The task includes clustering and hash learning as special cases. Deep neural networks are promising to be used because they can model the non-linearity of data and scale to large datasets. However, their model complexity is huge, and therefore, we need to carefully regularize the networks in order to learn useful representations that exhibit intended invariance for applications of interest. To this end, we propose a method called Information Maximizing Self-Augmented Training (IMSAT). In IMSAT, we use data augmentation to impose the invariance on discrete representations. More specifically, we encourage the predicted representations of augmented data points to be close to those of the original data points in an end-to-end fashion. At the same time, we maximize the information-theoretic dependency between data and their predicted discrete representations. Extensive experiments on benchmark datasets show that IMSAT produces state-of-the-art results for both clustering and unsupervised hash learning.