# GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering

arXiv: https://arxiv.org/abs/2002.11863 · HTML: https://mlsanity.com/paper/2002.11863/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2020.

## Built on by (most cited first, 30 of 32)

- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [ClusterLLM: Large Language Models as a Guide for Text Clustering](https://mlsanity.com/paper/2305.14871/) (2023)
- [Learning Representation for Clustering via Prototype Scattering and Positive Sampling](https://mlsanity.com/paper/2111.11821/) (2021)
- [MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering](https://mlsanity.com/paper/2105.01899/) (2021)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [Dense Semantic Contrast for Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/2109.07756/) (2021)
- [DivClust: Controlling Diversity in Deep Clustering](https://mlsanity.com/paper/2304.01042/) (2023)
- [Multi-domain Integrative Swin Transformer network for Sparse-View Tomographic Reconstruction](https://mlsanity.com/paper/2111.14831/) (2021)
- [Strongly Augmented Contrastive Clustering](https://mlsanity.com/paper/2206.00380/) (2022)
- [Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types](https://mlsanity.com/paper/2112.11573/) (2021)
- [Deep Clustering by Semantic Contrastive Learning](https://mlsanity.com/paper/2103.02662/) (2021)
- [Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection](https://mlsanity.com/paper/2205.00122/) (2022)
- [UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection](https://mlsanity.com/paper/2307.12540/) (2023)
- [Contextually Affinitive Neighborhood Refinery for Deep Clustering](https://mlsanity.com/paper/2312.07806/) (2023)
- [AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios](https://mlsanity.com/paper/2410.14379/) (2024)
- [Representation Learning for Clustering via Building Consensus](https://mlsanity.com/paper/2105.01289/) (2021)
- [Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation](https://mlsanity.com/paper/2303.16521/) (2023)
- [C3: Cross-instance guided Contrastive Clustering](https://mlsanity.com/paper/2211.07136/) (2022)
- [Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks](https://mlsanity.com/paper/2207.07173/) (2022)
- [Text-Guided Image Clustering](https://mlsanity.com/paper/2402.02996/) (2024)
- [Blind Localization and Clustering of Anomalies in Textures](https://mlsanity.com/paper/2404.12246/) (2024)
- [Heterogeneous Tri-stream Clustering Network](https://mlsanity.com/paper/2301.04451/) (2023)
- [Cequel: Cost-Effective Querying of Large Language Models for Text Clustering](https://mlsanity.com/paper/2504.15640/) (2025)
- [Deep Embedding Clustering Driven by Sample Stability](https://mlsanity.com/paper/2401.15989/) (2024)
- [Dataset Summarization by K Principal Concepts](https://mlsanity.com/paper/2104.03952/) (2021)
- [Information-Maximized Soft Variable Discretization for Self-Supervised Image Representation Learning](https://mlsanity.com/paper/2501.03469/) (2025)
- [ClusterFusion: Hybrid Clustering with Embedding Guidance and LLM Adaptation](https://mlsanity.com/paper/2512.04350/) (2025)
- [SensorSCAN: Self-Supervised Learning and Deep Clustering for Fault Diagnosis in Chemical Processes](https://mlsanity.com/paper/2208.08879/) (2022)

## Abstract (arXiv)

We propose a self-supervised Gaussian ATtention network for image Clustering (GATCluster). Rather than extracting intermediate features first and then performing the traditional clustering algorithm, GATCluster directly outputs semantic cluster labels without further post-processing. Theoretically, we give a Label Feature Theorem to guarantee the learned features are one-hot encoded vectors, and the trivial solutions are avoided. To train the GATCluster in a completely unsupervised manner, we design four self-learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping. Specifically, the transformation invariance and separability maximization tasks learn the relationships between sample pairs. The entropy analysis task aims to avoid trivial solutions. To capture the object-oriented semantics, we design a self-supervised attention mechanism that includes a parameterized attention module and a soft-attention loss. All the guiding signals for clustering are self-generated during the training process. Moreover, we develop a two-step learning algorithm that is memory-efficient for clustering large-size images. Extensive experiments demonstrate the superiority of our proposed method in comparison with the state-of-the-art image clustering benchmarks. Our code has been made publicly available at https://github.com/niuchuangnn/GATCluster.