Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization

2018-02-08 · ICLR 2018 1 · Ozsel Kilinc, Ismail Uysal

In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to each observation which is then modified by applying the domain specific transformation associated with the assigned label. Generated pseudo observation-label pairs are subsequently used to train a neural network with Auto-clustering Output Layer (ACOL) that introduces multiple softmax nodes for each pseudo parent-class. Due to the unsupervised objective based on Graph-based Activity Regularization (GAR) terms, softmax duplicates of each parent-class are specialized as the hidden information captured through the help of domain specific transformations is propagated during training. Ultimately we obtain a k-means friendly latent representation. Furthermore, we demonstrate how the chosen transformation type impacts performance and helps propagate the latent information that is useful in revealing unknown clusters. Our results show state-of-the-art performance for unsupervised clustering tasks on MNIST, SVHN and USPS datasets, with the highest accuracies reported to date in the literature.

📄 PDF Abstract BibTeX arXiv:1802.03063

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringUnsupervised Image Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need

2025-03-05 · Amal Shaheena, Nairouz Mrabahb, Riadh Ksantinia, Abdulla Alqaddoumia

The recent advances in deep clustering have been made possible by significant progress in self-supervised and pseudo-supervised learning. However, the trade-off between self-supervision and pseudo-supervision can give ri…

All Clustering Deep Clustering

Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting

2026-03-25 · Fan Chen, Shuyin Xia, Yi Wang arxiv

Single-source domain generalization for crowd counting is highly challenging because a single labeled source domain may contain heterogeneous latent domains, while unseen target domains often exhibit severe distribution …

Single-Source Domain Generalization Crowd Counting

Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning

2021-04-01 · Junhui Yin, Jiayan Qiu, Siqing Zhang, Jiyang Xie 외

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from …

Clustering Person Re-Identification Unsupervised Person Re-Identification

Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering

2023-05-23 · Xiaolin Zheng, Mengling Hu, Weiming Liu, Chaochao Chen 외

Short text clustering is challenging since it takes imbalanced and noisy data as inputs. Existing approaches cannot solve this problem well, since (1) they are prone to obtain degenerate solutions especially on heavy imb…

Clustering Contrastive Learning Pseudo Label Representation Learning+2

SPICE: Semantic Pseudo-labeling for Image Clustering

2021-03-17 · Chuang Niu, Hongming Shan, Ge Wang

The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity o…

Clustering Contrastive Learning Deep Clustering Image Clustering+3