DeepLab2: A TensorFlow Library for Deep Labeling
Abstract
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed DeepLab model variants with pretrained checkpoints as well as model training and evaluation code, allowing the community to reproduce and further improve upon the state-of-art systems. To showcase the effectiveness of DeepLab2, our Panoptic-DeepLab employing Axial-SWideRNet as network backbone achieves 68.0% PQ or 83.5% mIoU on Cityscaspes validation set, with only single-scale inference and ImageNet-1K pretrained checkpoints. We hope that publicly sharing our library could facilitate future research on dense pixel labeling tasks and envision new applications of this technology. Code is made publicly available at \url{https://github.com/google-research/deeplab2}.
Cite
@article{arxiv.2106.09748,
title = {DeepLab2: A TensorFlow Library for Deep Labeling},
author = {Mark Weber and Huiyu Wang and Siyuan Qiao and Jun Xie and Maxwell D. Collins and Yukun Zhu and Liangzhe Yuan and Dahun Kim and Qihang Yu and Daniel Cremers and Laura Leal-Taixe and Alan L. Yuille and Florian Schroff and Hartwig Adam and Liang-Chieh Chen},
journal= {arXiv preprint arXiv:2106.09748},
year = {2021}
}
Comments
4-page technical report. The first three authors contributed equally to this work