Thoughts on Objectives of Sparse and Hierarchical Masked Image Model
arXiv:2505.08819v1h-index: 2
Originality Synthesis-oriented
AI Analysis
This work addresses an incremental improvement in self-supervised learning for computer vision researchers.
The paper tackles the problem of improving masked image modeling by proposing a new mask pattern called Mesh Mask for the SparK model, reporting its effect on pre-training performance.
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.