AI Paper Atlas

Research map / Detection and segmentation / CNN features

MULLER: Multilayer Laplacian Resizer for Vision

Zhengzhong Tu, Peyman Milanfar, Hossein Talebi

ICCV 2023 · Detection and segmentation › CNN features · approach: Plain and high-resolution ViTs · 10 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
jointly finetune MaxViT-B with MULLER resizer 512->224MaxViT-B · ImageNet-1K valtop-1 accuracy: 84.95 -> 85.58Improved
jointly finetune MaxViT-T with MULLER resizer 512->224MaxViT-T · ImageNet-1K valtop-1 accuracy: 83.62 -> 83.95Improved
add MULLER resizer to ResNet-50ResNet-50 · ImageNet-1K valtop-1 accuracy: 75.3 -> 76.2Improved
add MULLER resizer to MobileNet-v2MobileNet-v2 · ImageNet-1K valtop-1 accuracy: 70.5 -> 71.8Improved
use MULLER instead of prior CNN learned resizer on EfficientNet-B0EfficientNet-B0 · ImageNet-1K valtop-1 accuracy: 77.9 -> 78.2Improved
use MULLER instead of prior CNN learned resizer on ResNet-50ResNet-50 · ImageNet-1K valtop-1 accuracy: 76.2 -> 76.2No clear effect
add MULLER to MaxViT-B for COCO detection at 640x640MaxViT-B Mask R-CNN · COCO2017 valbox AP: 51.6 -> 52.3Improved
add MULLER to MaxViT-T for image aesthetic assessmentMaxViT-T · AVAPLCC: 0.707 -> 0.729Improved
vary number of MULLER layers (2, 3, 4, 6) (ablation)MULLER on MaxViT-B · ImageNet-1K valtop-1 accuracy: 85.58 -> 85.50No clear effect
vary Gaussian kernel size and std of MULLER (ablation)MULLER on MaxViT-B · ImageNet-1K valtop-1 accuracy: 85.48 -> 85.58No clear effect
increase MULLER input resolution from 512 to 768 for 224 output (ablation)MULLER on MaxViT-B · ImageNet-1K valtop-1 accuracy: 85.58 -> 85.56No clear effect
reduce MULLER input resolution from 512 to 384 for 224 output (ablation)MULLER on MaxViT-B · ImageNet-1K valtop-1 accuracy: 85.58 -> 85.45Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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