Transformer-in-Computer-Vision

Why we included this project

Keeping a Transformer-in-computer-vision paper list current is real work, and this one was refreshed as recently as late 2025. Rather than a flat bibliography, the papers are grouped by task, from detection and depth estimation to diffusion, anomaly detection, and federated learning, so you can follow one subfield without wading through everything at once. Code links appear where authors provide them, which makes it easy to move from a survey article to a concrete implementation worth studying. Researchers choosing a baseline for their own experiments, or anyone starting a literature review in a fast-moving area, will find this a practical first stop.