Saved in:
Bibliographic Details
Main Authors: Miyazaki, Asahi, Okita, Tsuyoshi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.08819
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918019416981504
author Miyazaki, Asahi
Okita, Tsuyoshi
author_facet Miyazaki, Asahi
Okita, Tsuyoshi
contents Masked image modeling is one of the most poplular objectives of training. Recently, the SparK model has been proposed with superior performance among self-supervised learning models. This paper proposes a new mask pattern for this SparK model, proposing it as the Mesh Mask-ed SparK model. We report the effect of the mask pattern used for image masking in pre-training on performance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thoughts on Objectives of Sparse and Hierarchical Masked Image Model
Miyazaki, Asahi
Okita, Tsuyoshi
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Masked image modeling is one of the most poplular objectives of training. Recently, the SparK model has been proposed with superior performance among self-supervised learning models. This paper proposes a new mask pattern for this SparK model, proposing it as the Mesh Mask-ed SparK model. We report the effect of the mask pattern used for image masking in pre-training on performance.
title Thoughts on Objectives of Sparse and Hierarchical Masked Image Model
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.08819