Improve vision transformer by using anti-aliasing


Improve vision transformer by using anti-aliasing

Blending Anti-Aliasing into Vision Transformer
arXiv paper abstract
arXiv PDF paper

The transformer architectures, based on self-attention mechanism and convolution-free design, recently found superior performance and booming applications in computer vision.

However, the discontinuous patch-wise tokenization process implicitly introduces jagged artifacts into attention maps

… analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties.

… propose a plug-and-play Aliasing-Reduction Module(ARM) to alleviate the aforementioned issue.

We investigate the effectiveness and generalization of the proposed method across multiple tasks and various vision transformer families.

This lightweight design consistently attains a clear boost over several famous structures. … improves data efficiency and robustness of vision transformers.

Stay up to date. Subscribe to my posts
Web site with my other posts by category


Photo by Timothy Dykes on Unsplash



AI News Clips by Morris Lee: News to help your R&D

A computer vision consultant in artificial intelligence and related hitech technologies 37+ years. Am innovator with 66+ patents and ready to help a firm's R&D.