Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Zhu, Jinjing"'
Unsupervised domain adaption (UDA) has emerged as a popular solution to tackle the divergence between the labeled source and unlabeled target domains. Recently, some research efforts have been made to leverage large vision-language models, such as CL
Externí odkaz:
http://arxiv.org/abs/2407.01842
Recently, Depth Anything Model (DAM) - a type of depth foundation model - reveals impressive zero-shot capacity for diverse perspective images. Despite its success, it remains an open question regarding DAM's performance on 360 images that enjoy a la
Externí odkaz:
http://arxiv.org/abs/2406.13378
Recent endeavors have been made to leverage self-supervised depth estimation as guidance in unsupervised domain adaptation (UDA) for semantic segmentation. Prior arts, however, overlook the discrepancy between semantic and depth features, as well as
Externí odkaz:
http://arxiv.org/abs/2402.03795
Source-free cross-modal knowledge transfer is a crucial yet challenging task, which aims to transfer knowledge from one source modality (e.g., RGB) to the target modality (e.g., depth or infrared) with no access to the task-relevant (TR) source data
Externí odkaz:
http://arxiv.org/abs/2401.05014
Despite the progress made in domain adaptation, solving Unsupervised Domain Adaptation (UDA) problems with a general method under complex conditions caused by label shifts between domains remains a formidable task. In this work, we comprehensively in
Externí odkaz:
http://arxiv.org/abs/2312.05024
Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets. Moreover,
Externí odkaz:
http://arxiv.org/abs/2310.04747
In this paper, we strive to answer the question "how to collaboratively learn convolutional neural network (CNN)-based and vision transformer (ViT)-based models by selecting and exchanging the reliable knowledge between them for semantic segmentation
Externí odkaz:
http://arxiv.org/abs/2307.12574
The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap of RGB ima
Externí odkaz:
http://arxiv.org/abs/2307.04470
The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For this reason
Externí odkaz:
http://arxiv.org/abs/2303.14360
Endeavors have been recently made to leverage the vision transformer (ViT) for the challenging unsupervised domain adaptation (UDA) task. They typically adopt the cross-attention in ViT for direct domain alignment. However, as the performance of cros
Externí odkaz:
http://arxiv.org/abs/2303.13434