Feature Clustering

Feature clustering aims to group similar data features together, improving the efficiency and effectiveness of machine learning models. Current research focuses on integrating feature clustering with various architectures, such as variational autoencoders and contrastive learning methods, to enhance anomaly detection, improve representation learning in limited-data scenarios (e.g., medical imaging), and optimize automated machine learning pipelines. This approach is proving valuable across diverse applications, including climate modeling, industrial anomaly detection, and medical diagnosis, by improving model performance and offering enhanced interpretability.

Papers

August 7, 2024

Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR
Yikui Zhai, Wenlve Zhou, Bing Sun, Jingwen Li, Qirui Ke, Zilu Ying, Junying Gan, Chaoyun Mai, Ruggero Donida Labati, Vincenzo Piuri, Fabio Scotti
Contrastive Learning Synthetic Aperture Radar Target Recognition Contrastive Self Supervision Instance Discrimination Feature Clustering

July 14, 2024

Harnessing Feature Clustering For Enhanced Anomaly Detection With Variational Autoencoder And Dynamic Threshold
Tolulope Ale, Nicole-Jeanne Schlegel, Vandana P. Janeja
Anomaly Detection Variational Autoencoder Multivariate Time Series Data Dynamic Threshold Feature Clustering

July 6, 2023

That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering
Jie Zhang, Masanori Suganuma, Takayuki Okatani
Visual Anomaly Detection Pixel Level Anomaly Feature Clustering

February 28, 2023

Towards Personalized Preprocessing Pipeline Search
Diego Martinez, Daochen Zha, Qiaoyu Tan, Xia Hu
Feature Clustering Preprocessing Pipeline

November 15, 2022

Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation
Yejia Zhang, Xinrong Hu, Nishchal Sapkota, Yiyu Shi, Danny Z. Chen
Contrastive Learning Self Supervised Medical Image Segmentation Self Supervised Contrastive Learning Contrastive Representation Learning Self Supervised Instance Feature Clustering

July 22, 2022

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection
Zhiwei Yang, Peng Wu, Jing Liu, Xiaotao Liu
Anomaly Detection Aggregation Network Memory Augmented Adaptive Clustering Feature Clustering

July 20, 2022

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition
Qinying Liu, Zilei Wang
Contrastive Learning Action Recognition Domain Feature Target Feature Feature Clustering

May 9, 2022

Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost van de Weijer
Domain Adaptation Source Free Domain Adaptation Unsupervised Clustering Simple Approach Dispersion Profile Feature Clustering

April 21, 2022

MedFACT: Modeling Medical Feature Correlations in Patient Health Representation Learning via Feature Clustering
Xinyu Ma, Xu Chu, Yasha Wang, Hailong Yu, Liantao Ma, Wen Tang, Junfeng Zhao
Feature Correlation Patient Representation Correlation Graph Feature Clustering

Feature Clustering

Papers

Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR

Harnessing Feature Clustering For Enhanced Anomaly Detection With Variational Autoencoder And Dynamic Threshold

That's BAD: Blind Anomaly Detection by Implicit Local Feature Clustering

Towards Personalized Preprocessing Pipeline Search

Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition

Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation

MedFACT: Modeling Medical Feature Correlations in Patient Health Representation Learning via Feature Clustering