Log In Sign Up

SPICE: Semantic Pseudo-labeling for Image Clustering

by   Chuang Niu, et al.

This paper presents SPICE, a Semantic Pseudo-labeling framework for Image ClustEring. Instead of using indirect loss functions required by the recently proposed methods, SPICE generates pseudo-labels via self-learning and directly uses the pseudo-label-based classification loss to train a deep clustering network. The basic idea of SPICE is to synergize the discrepancy among semantic clusters, the similarity among instance samples, and the semantic consistency of local samples in an embedding space to optimize the clustering network in a semantically-driven paradigm. Specifically, a semantic-similarity-based pseudo-labeling algorithm is first proposed to train a clustering network through unsupervised representation learning. Given the initial clustering results, a local semantic consistency principle is used to select a set of reliably labeled samples, and a semi-pseudo-labeling algorithm is adapted for performance boosting. Extensive experiments demonstrate that SPICE clearly outperforms the state-of-the-art methods on six common benchmark datasets including STL10, Cifar10, Cifar100-20, ImageNet-10, ImageNet-Dog, and Tiny-ImageNet. On average, our SPICE method improves the current best results by about 10 and clustering accuracy.


page 1

page 3

page 7


Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning

The pioneering method for unsupervised meta-learning, CACTUs, is a clust...

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

Recent advances in semi-supervised learning (SSL) demonstrate that a com...

Estimating Soft Labels for Out-of-Domain Intent Detection

Out-of-Domain (OOD) intent detection is important for practical dialog s...

Semantic-enhanced Image Clustering

Image clustering is an important, and open challenge task in computer vi...

Semantic Clustering based Deduction Learning for Image Recognition and Classification

The paper proposes a semantic clustering based deduction learning by mim...

Improving Unsupervised Image Clustering With Robust Learning

Unsupervised image clustering methods often introduce alternative object...

Code Repositories