AI Paper Atlas

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

Learning to Discover Novel Visual Categories via Deep Transfer Clustering

Kai Han, Andrea Vedaldi, Andrew Zisserman

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 323 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
add consistency constraint (Pi-model) to DEC-based DTC (ablation)DTC-Baseline · CIFAR-10ACC: 74.9% -> 87.5%Improved
add consistency constraint (Pi-model) to DEC-based DTC (ablation)DTC-Baseline · SVHNACC: 57.6% -> 60.9%Improved
add Pi consistency constraint to DTC (ablation)DTC-Baseline · CIFAR-100ACC: 72.1% -> 70.6%Hurt
add temporal ensembling (TE) to DTC (ablation)DTC-Baseline · CIFAR-100ACC: 72.1% -> 72.8%Improved
add temporal ensembling (TE) to DTC (ablation)DTC-Baseline · SVHNACC: 57.6% -> 55.8%Hurt
add temporal ensemble targets (TEP) to DTC (ablation)DTC-Baseline · CIFAR-10ACC: 74.9% -> 75.2%Mixed
add Pi consistency constraint to DTC (ablation)DTC-Baseline · OmniGlotACC: 87.9% -> 89.0%Improved
use estimated number of categories for KCL (ablation)KCL · ImageNet (unknown K)ACC: 65.2% -> 71.4%Improved
use estimated number of categories for MCL (ablation)MCL · OmniGlot (unknown K)ACC: 80.2% -> 80.5%Improved
use estimated number of categories for MCLMCL · ImageNet (unknown K)ACC: 71.5% -> 72.9%Improved
transfer from labelled-class feature extractor, DTC vs KCLKCL · CIFAR-10ACC: 66.5% -> 87.5%Improved
estimate unknown category number instead of assuming KDTC · OmniGlotACC: 89.0% -> 87.0%Hurt

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