Unified Perceptual Parsing for Scene Understanding

Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun
7/26/2018
cs.CV

Official code: CSAILVision/unifiedparsing (428 stars, MIT, last commit 2022-02-11).

Abstract

Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations. We benchmark our framework on Unified Perceptual Parsing and show that it is able to effectively segment a wide range of concepts from images. The trained networks are further applied to discover visual knowledge in natural scenes. Models are available at \url{https://github.com/CSAILVision/unifiedparsing}.

View on arXivView PDF

Code Implementations(1)

CSAILVision/unifiedparsingOfficial100%
MIT

Codebase and pretrained models for ECCV'18 Unified Perceptual Parsing

42869C, CudaJul 17, 20184 years agoMIT

Similar Papers

Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving

85% match2023

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

83% match2025

AHMAD: Adaptive Hybrid Multi-task Vision Learning with Assisted Distillation for Keypoint Detection

83% match2026

YOLOR-Based Multi-Task Learning

83% match1 repo2.0k2023

Unifying 3D Vision-Language Understanding via Promptable Queries

82% match1 repo862024

Semantic Understanding of Scenes through the ADE20K Dataset

82% match1 repo5.1k2016

Cite this paper

@article{xiao2018unified,
  title  = {Unified Perceptual Parsing for Scene Understanding},
  author = {Tete Xiao and Yingcheng Liu and Bolei Zhou and Yuning Jiang and Jian Sun},
  year   = {2018},
  eprint = {1807.10221},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1807.10221}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1807.10221.svg)](https://codeofpaper.com/paper/1807.10221)

Discussion