# SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations

Source: [SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations](<https://www.sota2.com/research/paper/68fa70551e209131cea4a55d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:39:07.726Z

Authors: Zhiming Wang, Lin Gu, Feng Lu

Published: 2023-08-17T09:43:14.000Z

## Abstract

Due to the prevalence of scale variance in nature images, we propose to use image scale as a self-supervised signal for Masked Image Modeling (MIM). Our method involves selecting random patches from the input image and downsampling them to a low-resolution format. Our framework utilizes the latest advances in super-resolution (SR) to design the prediction head, which reconstructs the input from low-resolution clues and other patches. After 400 epochs of pre-training, our Super Resolution Masked Autoencoders (SRMAE) get an accuracy of 82.1% on the ImageNet-1K task. Image scale signal also allows our SRMAE to capture scale invariance representation. For the very low resolution (VLR) recognition task, our model achieves the best performance, surpassing DeriveNet by 1.3%. Our method also achieves an accuracy of 74.84% on the task of recognizing low-resolution facial expressions, surpassing the current state-of-the-art FMD by 9.48%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.08884>)

[PDF](<https://arxiv.org/pdf/2308.08884.pdf>)