SCENIC: A JAX Library for Computer Vision Research and Beyond

10/18/2021
by   Mostafa Dehghani, et al.
31

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/28/2017

ChainerCV: a Library for Deep Learning in Computer Vision

Despite significant progress of deep learning in the field of computer v...
research
12/08/2021

FLAVA: A Foundational Language And Vision Alignment Model

State-of-the-art vision and vision-and-language models rely on large-sca...
research
09/21/2020

A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

This work presents Kornia, an open source computer vision library built ...
research
03/19/2022

Volkit: A Performance-Portable Computer Vision Library for 3D Volumetric Data

We present volkit, an open source library with high performance implemen...
research
10/05/2019

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

This work presents Kornia -- an open source computer vision library whic...
research
03/29/2021

LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis

Recent advances in document image analysis (DIA) have been primarily dri...
research
02/07/2020

Input Dropout for Spatially Aligned Modalities

Computer vision datasets containing multiple modalities such as color, d...

Please sign up or login with your details

Forgot password? Click here to reset