awesome-attention-mechanism-in-cv

Why we included this project

Attention modules show up in nearly every modern vision paper, but keeping track of them is another matter. This list gathers dozens of attention mechanisms and plug-and-play modules into a single table, with each entry pointing to the original paper, a reference implementation, and often a blog post that explains the idea. That makes it useful for researchers surveying the field and for engineers who want a quick look at a reference codebase before deciding whether a module is worth testing in their own pipeline. Vision transformers get their own section, which helps when you are comparing attention-based architectures rather than just channel or spatial attention blocks. It is a discovery aid rather than runnable software, so treat it as a map of the field instead of something to install.