Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Shen, Ghosh, Anurag, Narasimhan, Srinivasa G.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910727320633344
author Zheng, Shen
Ghosh, Anurag
Narasimhan, Srinivasa G.
author_facet Zheng, Shen
Ghosh, Anurag
Narasimhan, Srinivasa G.
contents Driving is challenging in conditions like night, rain, and snow. Lack of good labeled datasets has hampered progress in scene understanding under such conditions. Unsupervised Domain Adaptation (UDA) using large labeled clear-day datasets is a promising research direction in such cases. However, many UDA methods are trained with dominant scene backgrounds (e.g., roads, sky, sidewalks) that appear dramatically different across domains. As a result, they struggle to learn effective features of smaller and often sparse foreground objects (e.g., people, vehicles, signs). In this work, we improve UDA training by applying in-place image warping to focus on salient objects. We design instance-level saliency guidance to adaptively oversample object regions and undersample background areas, which reduces adverse effects from background context and enhances backbone feature learning. Our approach improves adaptation across geographies, lighting, and weather conditions, and is agnostic to the task (segmentation, detection), domain adaptation algorithm, saliency guidance, and underlying model architecture. Result highlights include +6.1 mAP50 for BDD100K Clear $\rightarrow$ DENSE Foggy, +3.7 mAP50 for BDD100K Day $\rightarrow$ Night, +3.0 mAP50 for BDD100K Clear $\rightarrow$ Rainy, and +6.3 mIoU for Cityscapes $\rightarrow$ ACDC. Besides, Our method adds minimal training memory and no additional inference latency. Code is available at https://github.com/ShenZheng2000/Instance-Warp
format Preprint
id arxiv_https___arxiv_org_abs_2403_12712
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation
Zheng, Shen
Ghosh, Anurag
Narasimhan, Srinivasa G.
Computer Vision and Pattern Recognition
Machine Learning
Driving is challenging in conditions like night, rain, and snow. Lack of good labeled datasets has hampered progress in scene understanding under such conditions. Unsupervised Domain Adaptation (UDA) using large labeled clear-day datasets is a promising research direction in such cases. However, many UDA methods are trained with dominant scene backgrounds (e.g., roads, sky, sidewalks) that appear dramatically different across domains. As a result, they struggle to learn effective features of smaller and often sparse foreground objects (e.g., people, vehicles, signs). In this work, we improve UDA training by applying in-place image warping to focus on salient objects. We design instance-level saliency guidance to adaptively oversample object regions and undersample background areas, which reduces adverse effects from background context and enhances backbone feature learning. Our approach improves adaptation across geographies, lighting, and weather conditions, and is agnostic to the task (segmentation, detection), domain adaptation algorithm, saliency guidance, and underlying model architecture. Result highlights include +6.1 mAP50 for BDD100K Clear $\rightarrow$ DENSE Foggy, +3.7 mAP50 for BDD100K Day $\rightarrow$ Night, +3.0 mAP50 for BDD100K Clear $\rightarrow$ Rainy, and +6.3 mIoU for Cityscapes $\rightarrow$ ACDC. Besides, Our method adds minimal training memory and no additional inference latency. Code is available at https://github.com/ShenZheng2000/Instance-Warp
title Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.12712