SCENIC: A JAX Library for Computer Vision Research and Beyond
This toolkit addresses the need for efficient prototyping and experimentation in vision research, though it is incremental as it builds on existing JAX and Transformer frameworks.
The authors introduced SCENIC, a JAX library designed to accelerate Transformer-based model research in computer vision and other domains, enabling rapid experimentation and prototyping with support for diverse tasks and large-scale training.
Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond. The goal of this toolkit is to facilitate rapid experimentation, prototyping, and research of new vision architectures and models. Scenic supports a diverse range of vision tasks (e.g., classification, segmentation, detection)and facilitates working on multi-modal problems, along with GPU/TPU support for multi-host, multi-device large-scale training. Scenic also offers optimized implementations of state-of-the-art research models spanning a wide range of modalities. Scenic has been successfully used for numerous projects and published papers and continues serving as the library of choice for quick prototyping and publication of new research ideas.