FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation

12/08/2016
by   Judy Hoffman, et al.
0

Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a human observer. For example, training on one city and testing on another in a different geographic region and/or weather condition may result in significantly degraded performance due to pixel-level distribution shift. In this paper, we introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems. Our method consists of both global and category specific adaptation techniques. Global domain alignment is performed using a novel semantic segmentation network with fully convolutional domain adversarial learning. This initially adapted space then enables category specific adaptation through a generalization of constrained weak learning, with explicit transfer of the spatial layout from the source to the target domains. Our approach outperforms baselines across different settings on multiple large-scale datasets, including adapting across various real city environments, different synthetic sub-domains, from simulated to real environments, and on a novel large-scale dash-cam dataset.

READ FULL TEXT

page 1

page 3

page 7

page 8

research
04/23/2018

Fully Convolutional Adaptation Networks for Semantic Segmentation

The recent advances in deep neural networks have convincingly demonstrat...
research
02/28/2018

Learning to Adapt Structured Output Space for Semantic Segmentation

Convolutional neural network-based approaches for semantic segmentation ...
research
11/27/2019

Class-Conditional Domain Adaptation on Semantic Segmentation

Semantic segmentation is an important sub-task for many applications, bu...
research
05/13/2020

SRDA-Net: Super-Resolution Domain Adaptation Networks for Semantic Segmentation

Recently, Unsupervised Domain Adaptation (UDA) was proposed to address t...
research
11/08/2017

CyCADA: Cycle-Consistent Adversarial Domain Adaptation

Domain adaptation is critical for success in new, unseen environments. A...
research
08/06/2021

BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

Semantic segmentation aims to predict pixel-level labels. It has become ...
research
12/10/2020

Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation

Adapting semantic segmentation models to new domains is an important but...

Please sign up or login with your details

Forgot password? Click here to reset