mlsanityData to 14 Oct 2026

Thoughts on Objectives of Sparse and Hierarchical Masked Image Model

arXiv 2505.08819 ↗First posted 12 May 2025eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 4 of its 5 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

4 of 5 references.

References · 4

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  3. 2023Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modelingcited by 94
  4. 2023Improving Pixel-based MIM by Reducing Wasted Modeling Capabilitycited by 24

Built on by

Not cited yet.