AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Unsupervised Part Discovery via Dual Representation Alignment

Jiahao Xia, Wenjian Huang, Min Gang Xu, Jianguo Zhang, Haimin Zhang, Ziyu Sheng, Dong Xu

TPAMI 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery

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 area loss (ablation)Ours (DINO pretrained) · CUB-FNMI: 1.8 -> 45.2Improved
add concentration loss (ablation)Ours (DINO pretrained) · CUB-FNMI: 5.2 -> 45.2Improved
add reconstruction loss (ablation)Ours (DINO pretrained) · CUB-FNMI: 15.9 -> 45.2Improved
add semantic consistency loss (ablation)Ours (DINO pretrained) · CUB-FNMI: 41.3 -> 45.2Improved
exchange part representations between paired images (ablation)Ours (DINO pretrained) · CUB-F (rotation 0 deg)NMI: 43.6 -> 45.2Improved
use DINO ImageNet pretraining for the feature encoderOurs · CUB-FNMI: 22.0 -> 45.2Improved
use DINO ImageNet pretraining for the feature encoderOurs · CelebA-in-the-wild (K=8)inter-ocular NME: 8.70% -> 10.24%Hurt
use DINO ImageNet pretraining for the feature encoderOurs · PartImageNetNMI: 22.13 -> 27.85Improved
use MAE instead of no pretraining (ablation)Ours (ViT-B/16) · CelebA-in-the-wild (K=8)NMI: 50.5 -> 59.5Improved
use DINO instead of no pretraining (ablation)Ours (ViT-B/16) · CelebA-in-the-wild (K=8)NMI: 50.5 -> 43.7Hurt
use MoCo v3 instead of no pretraining (ablation)Ours (ViT-B/16) · CelebA-in-the-wild (K=8)NMI: 50.5 -> 22.0Hurt
use perceptual loss instead of MSE reconstruction loss (ablation)Ours (no pretraining) · CelebA-in-the-wild (K=8)inter-ocular NME: 16.70% -> 8.70%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