DeepLab2: A TensorFlow Library for Deep Labeling

2021/06/17 by Mark Weber, Weber, Mark, Huiyu Wang +29 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Medical Image Segmentation Techniques #cs.CV

paper · pdf · doi:10.48550/arxiv.2106.09748

4-page technical report. The first three authors contributed equally to this work

arxiv created 2021/06/17 · openalex publication_date 2021/06/17 · arxiv updated 2021/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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 \urlhttps://github.com/google-research/deeplab2.

Citations

• The Pascal Visual Object Classes (VOC) Challenge
• Gradient-based learning applied to document recognition
• Vision meets robotics: The KITTI dataset
• ImageNet Large Scale Visual Recognition Challenge
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Semantic Understanding of Scenes Through the ADE20K Dataset
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Rethinking Atrous Convolution for Semantic Image Segmentation
• AutoAugment: Learning Augmentation Policies from Data
• DeeperLab: Single-Shot Image Parser
• Axial Attention in Multidimensional Transformers
• Tracking Objects as Points
• Scaling Wide Residual Networks for Panoptic Segmentation
• STEP: Segmenting and Tracking Every Pixel

Cited by

• Weakly-supervised Localization of Manipulated Image Regions Using Multi-resolution Learned Features

Related

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• TensorFlow: A system for large-scale machine learning
• Detect, Replace, Refine: Deep Structured Prediction For Pixel Wise Labeling
• fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence
• qlty: handling large tensors in scientific imaging