Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation

08/23/2022
by   Weihao Yan, et al.
0

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can provide accurate annotations. However, the performance of the semantic segmentation model trained with the data of the simulator will significantly decrease when applied in the actual scene. Unsupervised domain adaptation (UDA) for semantic segmentation has recently gained increasing research attention, aiming to reduce the domain gap and improve the performance on the target domain. In this paper, we propose a novel two-stage entropy-based UDA method for semantic segmentation. In stage one, we design a threshold-adaptative unsupervised focal loss to regularize the prediction in the target domain, which has a mild gradient neutralization mechanism and mitigates the problem that hard samples are barely optimized in entropy-based methods. In stage two, we introduce a data augmentation method named cross-domain image mixing (CIM) to bridge the semantic knowledge from two domains. Our method achieves state-of-the-art 58.4 GTA5-to-Cityscapes using DeepLabV2 and competitive performance using the lightweight BiSeNet.

READ FULL TEXT

page 1

page 4

page 5

page 7

page 8

page 10

research
09/02/2019

Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation

Deep learning-based semantic segmentation methods have an intrinsic limi...
research
08/12/2022

Domain-invariant Prototypes for Semantic Segmentation

Deep Learning has greatly advanced the performance of semantic segmentat...
research
11/08/2018

Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels

Training deep networks for semantic segmentation requires annotation of ...
research
03/08/2021

Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation

Data-driven based approaches, in spite of great success in many tasks, h...
research
05/23/2019

Incorporating Human Domain Knowledge in 3D LiDAR-based Semantic Segmentation

This work studies semantic segmentation using 3D LiDAR data. Popular dee...
research
08/12/2022

Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation

In unsupervised domain adaptive (UDA) semantic segmentation, the distill...
research
11/20/2019

Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation

It is expensive to generate real-life image labels and there is a domain...

Please sign up or login with your details

Forgot password? Click here to reset