AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

Md Ashiqur Rahman, Chiao-An Yang, Michael N. Cheng, Lim Jun Hao, Jeremiah Jiang, Teck-Yian Lim, Raymond A. Yeh

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 0 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 DEC latent canonicalizer instead of augmentation plus equivariance loss (AugL)ViT/Swin/DINOv2 segmentation · Locally scaled segmentationmIoU: AugL 79.05 -> 80.86 on DINOv2Improved
canonicalize the input image (Canon) instead of latent features (ablation)Aug-trained models · Locally scaled segmentation (ViT)mIoU: 82.18 -> 79.37Hurt
input-level Canon on locally scaled ImageNet (ablation)Base models · Locally scaled ImageNet (Swin)Top-1 accuracy: 77.94 -> 74.67Hurt
add monotone scale equivariance loss (AugL) on top of Aug (ablation)ViT segmentation · Locally scaled segmentationmIoU: 82.18 -> 82.35No clear effect
add DEC on top of Aug for MNIST classificationSwin (MNIST) · Locally scaled MNIST overallAccuracy: 93.93 -> 96.53Improved
add DEC to pretrained models for locally scaled ImageNetViT, DeiT, Swin, BEiT · Locally scaled ImageNetTop-1 accuracy: 80.15 -> 80.36 (ViT); 77.94 -> 78.32 (Swin)Improved
add an invariance loss (InvL) to Aug on ImageNet (ablation)ViT, Swin · Locally scaled ImageNetTop-1 accuracy: 80.15 -> 80.16No clear effect
DEC amortized fixed-point solver instead of differentiable optimization canonicalization (ablation)DEC · Training batch 10, 224x224GPU memory: 43.30 GB -> 5.75 GBImproved
apply several DEC modules throughout the network instead of only at the input (ablation)DEC · Scale-MNISTAccuracyImproved
add DEC to hierarchical modelsHRViT, ResFormer · Scale-MNISTAccuracy: ResFormer Inv-loss 94.92 -> 96.91Improved

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