Graphonomy: Universal Human Parsing via Graph Transfer Learning

04/09/2019
by   Ke Gong, et al.
0

Prior highly-tuned human parsing models tend to fit towards each dataset in a specific domain or with discrepant label granularity, and can hardly be adapted to other human parsing tasks without extensive re-training. In this paper, we aim to learn a single universal human parsing model that can tackle all kinds of human parsing needs by unifying label annotations from different domains or at various levels of granularity. This poses many fundamental learning challenges, e.g. discovering underlying semantic structures among different label granularity, performing proper transfer learning across different image domains, and identifying and utilizing label redundancies across related tasks. To address these challenges, we propose a new universal human parsing agent, named "Graphonomy", which incorporates hierarchical graph transfer learning upon the conventional parsing network to encode the underlying label semantic structures and propagate relevant semantic information. In particular, Graphonomy first learns and propagates compact high-level graph representation among the labels within one dataset via Intra-Graph Reasoning, and then transfers semantic information across multiple datasets via Inter-Graph Transfer. Various graph transfer dependencies (, similarity, linguistic knowledge) between different datasets are analyzed and encoded to enhance graph transfer capability. By distilling universal semantic graph representation to each specific task, Graphonomy is able to predict all levels of parsing labels in one system without piling up the complexity. Experimental results show Graphonomy effectively achieves the state-of-the-art results on three human parsing benchmarks as well as advantageous universal human parsing performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 9

research
01/26/2021

Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer

Prior highly-tuned image parsing models are usually studied in a certain...
research
02/18/2020

Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

The dominant object detection approaches treat each dataset separately a...
research
11/27/2019

Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing

Human parsing, or human body part semantic segmentation, has been an act...
research
10/22/2019

Transductive Parsing for Universal Decompositional Semantics

We introduce a transductive model for parsing into Universal Decompositi...
research
05/01/2018

Multitask Parsing Across Semantic Representations

The ability to consolidate information of different types is at the core...
research
12/22/2021

Toward Educator-focused Automated Scoring Systems for Reading and Writing

This paper presents methods for improving automated essay scoring with t...
research
09/14/2020

GINet: Graph Interaction Network for Scene Parsing

Recently, context reasoning using image regions beyond local convolution...

Please sign up or login with your details

Forgot password? Click here to reset