AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Diego Marcos

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining · 5 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 concentration prior with total variation prior on a self-supervised ViT backbonePDiscoNet vs PDiscoFormer · CUB (K=16)ARI: 43.41 -> 55.83Improved
replace concentration prior with total variation prior on irregular multi-instance partsPDiscoNet + ViT-B vs PDiscoFormer · Oxford Flowers (K=8)foreground mIoU: 13.18 -> 69.59Improved
add total variation loss (ablation)PDiscoFormer · PartImageNet OOD (K=25)ARI: 25.35 -> 59.27Improved
add total variation loss (ablation)PDiscoFormer · CUB (K=16)Top-1 accuracy: 80.22 -> 88.72Improved
add equivariance loss (ablation)PDiscoFormer · CUB (K=16)ARI: 30.63 -> 55.83Improved
add per-part layer normalization modulation (ablation)PDiscoFormer · CUB (K=16)Top-1 accuracy: 69.73 -> 88.72Improved
add presence loss L_p1 (each part present at least once per batch) (ablation)PDiscoFormer · CUB (K=16)ARI: 34.28 -> 55.83Improved
add background presence loss L_p0 (ablation)PDiscoFormer · PartImageNet OOD (K=25)ARI: 49.08 -> 59.27Improved
add Gumbel-Softmax instead of Softmax on part maps (ablation)PDiscoFormer · CUB (K=16)ARI: 43.61 -> 55.83Improved
add orthogonality loss (ablation)PDiscoFormer · PartImageNet OOD (K=25)ARI: 58.86 -> 59.27No clear effect
add entropy loss (ablation)PDiscoFormer · PartImageNet OOD (K=25)Top-1 accuracy: 91.19 -> 90.77 accuracy; NMI 39.16 -> 44.71Mixed
use DINOv2 ViT-B instead of ResNet-101 backbone with the TV-based losses (ablation)PDiscoFormer · Oxford FlowersTop-1 accuracy: 8.41 -> 99.61 (K=2)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