AI Paper Atlas

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

Visual Recognition with Deep Nearest Centroids

Wenguan Wang, Cheng Han, Tianfei Zhou, Dongfang Liu

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 45 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
Replace a parametric softmax classifier with DNCResNet classification models · CIFAR-10 testtop-1 accuracy: 95.55% -> 95.78%; 95.58% -> 95.82%Improved
Replace a parametric softmax classifier with DNCResNet and Swin classification models · ImageNet valtop-1 accuracy: 76.20% -> 76.49%; 77.52% -> 77.80%; 83.02% -> 83.26%; 83.36% -> 83.68%Improved
Replace a parametric softmax classifier with DNCResNet classification models · CIFAR-100 testtop-1 accuracy: 79.81% -> 79.91%; 79.83% -> 79.99%Improved
Use DNC classification and an ImageNet-pretrained DNC backboneFCN with ResNet101 · ADE20K valmIoU: 39.9% -> 42.3%Improved
Use DNC classification and an ImageNet-pretrained DNC backboneFCN with ResNet101 · Cityscapes valmIoU: 75.6% -> 77.5%Improved
Use DNC classification and an ImageNet-pretrained DNC backboneDeepLabV3 with ResNet101 · ADE20K valmIoU: 44.1% -> 45.7%Improved
Use DNC classification and an ImageNet-pretrained DNC backboneUperNet with Swin-B · ADE20K valmIoU: 48.0% -> 50.5%Improved
Anchor class sub-centroids to actual training images instead of cluster centers (ablation)DNC-ResNet50 · ImageNet valtop-1 accuracy: 76.49% -> 76.37%Hurt
Increase class representatives from one centroid to four sub-centroids (ablation)DNC-ResNet101 · ImageNet valtop-1 accuracy: 77.31% -> 77.80%Improved
Increase class representatives from one centroid to ten sub-centroids (ablation)DNC-DeepLabV3 · ADE20K valmIoU: 43.2% -> 44.3%Improved
Increase the number of class sub-centroids from ten to twenty (ablation)DNC-DeepLabV3 · ADE20K valmIoU: 44.3% -> 44.0%Hurt
Increase external memory size (ablation)DNC-ResNet101 · ImageNet valtop-1 accuracy: 77.49% -> 77.80%Improved

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