SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.09382 · 2021

SPICE: Semantic Pseudo-labeling for Image Clustering

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling, and reliable pseudo-labeling, which enable accurate and reliable self-supervision over clustering. Without using any ground-truth label, we optimize the clustering network in three stages: 1) train the feature model through contrastive learning to measure the instance similarity, 2) train the clustering head with the prototype pseudo-labeling algorithm to identify cluster semantics, and 3) jointly train the feature model and clustering head with the reliable pseudo-labeling algorithm to improve the clustering performance. Extensive experimental results demonstrate that SPICE achieves significant improvements (~10%) over existing methods and establishes the new state-of-the-art clustering results on six image benchmark datasets in terms of three popular metrics. Importantly, SPICE significantly reduces the gap between unsupervised and fully-supervised classification; e.g., there is only a 2% (91.8% vs 93.8%) accuracy difference on CIFAR-10. Our code has been made publically available at https://github.com/niuchuangnn/SPICE.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.09382")
get_code_for_paper("2103.09382")
have("2103.09382")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.09382.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.09382.svg)](https://syntology.ai/paper/2103.09382)

Connect an agent — have() is free.