DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation

04/16/2018
by   Zuxuan Wu, et al.
0

Harvesting dense pixel-level annotations to train deep neural networks for semantic segmentation is extremely expensive and unwieldy at scale. While learning from synthetic data where labels are readily available sounds promising, performance degrades significantly when testing on novel realistic data due to domain discrepancies. We present Dual Channel-wise Alignment Networks (DCAN), a simple yet effective approach to reduce domain shift at both pixel-level and feature-level. Exploring statistics in each channel of CNN feature maps, our framework performs channel-wise feature alignment, which preserves spatial structures and semantic information, in both an image generator and a segmentation network. In particular, given an image from the source domain and unlabeled samples from the target domain, the generator synthesizes new images on-the-fly to resemble samples from the target domain in appearance and the segmentation network further refines high-level features before predicting semantic maps, both of which leverage feature statistics of sampled images from the target domain. Unlike much recent and concurrent work relying on adversarial training, our framework is lightweight and easy to train. Extensive experiments on adapting models trained on synthetic segmentation benchmarks to real urban scenes demonstrate the effectiveness of the proposed framework.

READ FULL TEXT

page 4

page 11

page 13

research
04/19/2019

Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes

Semantic segmentation, a pixel-level vision task, is developed rapidly b...
research
04/23/2018

Fully Convolutional Adaptation Networks for Semantic Segmentation

The recent advances in deep neural networks have convincingly demonstrat...
research
04/02/2020

Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation

Learning segmentation from synthetic data and adapting to real data can ...
research
06/08/2021

Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation

Convolutional neural networks may perform poorly when the test and train...
research
09/07/2020

Channel-wise Alignment for Adaptive Object Detection

Generic object detection has been immensely promoted by the development ...
research
05/16/2023

Towards Pragmatic Semantic Image Synthesis for Urban Scenes

The need for large amounts of training and validation data is a huge con...
research
12/24/2018

A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes

During the last half decade, convolutional neural networks (CNNs) have t...

Please sign up or login with your details

Forgot password? Click here to reset