AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Deep Clustering for Unsupervised Learning of Visual Features

Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 2,745 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on ImageNet instead of uncurated YFCC100M images (ablation)DeepCluster · Pascal VOC 2007 classification (fc6-8 only)mAP: 67.3 -> 72.0Improved
pre-train on uncurated YFCC100M (ablation)DeepCluster · Pascal VOC transfermAP: up to +4.3% on classification and +4.5% on semantic segmentation over prior artNo clear effect
use Sobel preprocessing instead of raw RGB input (ablation)DeepCluster · ImageNet linear probe conv5accuracy (%): 30.6 -> 38.2Improved
use k-means instead of PIC graph clustering (ablation)DeepCluster · Pascal VOC 2007 classification (fc6-8 only)mAP: 71.0 -> 72.0Improved
use PIC instead of k-means clustering (ablation)DeepCluster · Pascal VOC 2007 detection (fc6-8 only)mAP: 51.4 -> 53.6Mixed
use k-means instead of PIC on ImageNet MLP retraining (ablation)DeepCluster · ImageNet classification (fc6-8 retrained)Acc@1: 44.0 -> 45.9Hurt
use a deeper VGG-16 instead of AlexNet (ablation)DeepCluster · Pascal VOC 2007 detectionmAP: 55.4 -> 65.9Improved
average over 10 crops instead of a single cropDeepCluster · ImageNet linear probe conv5accuracy (%): 36.1 -> 38.2Improved
apply unsupervised pretraining with DeepCluster instead of random initDeepCluster · Pascal VOC 2007 classification (fc6-8 only)mAP: 29.0 -> 70.4Improved
use Sobel filtering on supervised VGG-16 inputsupervised VGG-16 · Oxford5K instance retrievalmAP: 5.5 points mAP gain on Oxford, not on ParisImproved
train longer than 400 epochsDeepCluster · Pascal VOC classification (no fine-tuning)mAPNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy