AI Paper Atlas

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

Deep Adaptive Image Clustering

Jianlong Chang, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 584 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 Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation)DAC · MNISTACC: 0.9660 -> 0.9775Improved
add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation)DAC · CIFAR-10ACC: 0.4982 -> 0.5218Improved
add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation)DAC · CIFAR-100ACC: 0.2189 -> 0.2375Improved
add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation)DAC · STL-10ACC: 0.4337 -> 0.4699Improved
add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation)DAC · ImageNet-10ACC: 0.5026 -> 0.5272Improved
add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation)DAC · ImageNet-DogACC: 0.2455 -> 0.2748Improved
cluster by argmax of label features instead of K-means on the learned features (ablation)DAC · MNISTACC: 0.9761 -> 0.9775Improved
cluster by argmax of label features instead of K-means on the learned features (ablation)DAC · CIFAR-10ACC: 0.5106 -> 0.5218Improved
cluster by argmax of label features instead of K-means on the learned features (ablation)DAC · ImageNet-DogACC: 0.2709 -> 0.2748Improved
single-stage DAC versus multi-stage DECDAC · CIFAR-10ACC: 0.3010 -> 0.5218Improved
single-stage DAC versus JULEDAC · CIFAR-10ACC: 0.2715 -> 0.5218Improved
use learned representation (AE) before K-means instead of raw pixel K-meansK-means · MNISTACC: 0.5723 -> 0.8123Improved

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