SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.02859 · ICCV · 2023

MULLER: Multilayer Laplacian Resizer for Vision

Zhengzhong Tu, Peyman Milanfar, Hossein Talebi

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Image resizing operation is a fundamental preprocessing module in modern computer vision. Throughout the deep learning revolution, researchers have overlooked the potential of alternative resizing methods beyond the commonly used resizers that are readily available, such as nearest-neighbors, bilinear, and bicubic. The key question of our interest is whether the front-end resizer affects the performance of deep vision models? In this paper, we present an extremely lightweight multilayer Laplacian resizer with only a handful of trainable parameters, dubbed MULLER resizer. MULLER has a bandpass nature in that it learns to boost details in certain frequency subbands that benefit the downstream recognition models. We show that MULLER can be easily plugged into various training pipelines, and it effectively boosts the performance of the underlying vision task with little to no extra cost. Specifically, we select a state-of-the-art vision Transformer, MaxViT [50], as the baseline, and show that, if trained with MULLER, MaxViT gains up to 0.6% top-1 accuracy, and meanwhile enjoys 36% inference cost saving to achieve similar top-1 accuracy on ImageNet-1k, as compared to the standard training scheme. Notably, MULLER's performance also scales with model size and training data size such as ImageNet-21k and JFT, and it is widely applicable to multiple vision tasks, including image classification, object detection and segmentation, as well as image quality assessment. The code is available at https://github.com/google-research/ google-research/tree/master/muller.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.02859")
get_code_for_paper("2304.02859")
have("2304.02859")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2304.02859.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2304.02859.svg)](https://syntology.ai/paper/2304.02859)

Connect an agent — have() is free.