Self-Mutating Network for Domain Adaptive Segmentation of Aerial Images

Lee, Kyungsu; Lee, Haeyun; Hwang, Jae Youn

doi:10.1109/iccv48922.2021.00698

Cited by 10 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of method faces more challenging issues than a traditional person Re‐ID system. Relevant research efforts, which have recently become popular, mainly focus on the basic work of constructing datasets, such as DOTA, 6 NWPU VHR, 21 UAV123, 22 VisDrone, 23 AVI, 24 and PRAI‐1581, 7 and the tasks of object detection, 10 tracking, 11 and segmentation 12 . Regarding the person Re‐ID task, which receives little attention, Zhang et al 7 presented an end‐to‐end learning method with a subspace pool using convolution feature mapping; this approach learns discriminative and compact feature representations to represent pedestrian images, effectively improving the accuracy of person Re‐ID in aerial imagery.…”

Section: Related Workmentioning

confidence: 99%

“…In addition to the existing problems faced by traditional person Re‐ID approaches, aerial person Re‐ID methods are also required to handle issues such as weak pedestrian appearance features and large resolution variations in aerial imagery due to interference factors, including UAV shooting height inconsistencies, UAV camera motion angle changes and wide‐angle distortion. Recently, aerial imagery has been widely analyzed in the computer vision community, while its application to person Re‐ID has just started to be explored 10‐12 . The current state‐of‐the‐art works related to aerial person Re‐ID still adopt traditional deep learning methods 7 .…”

Section: Introductionmentioning

confidence: 99%

“…Recently, aerial imagery has been widely analyzed in the computer vision community, while its application to person Re-ID has just started to be explored. [10][11][12] The current state-of-the-art works related to aerial person Re-ID still adopt traditional deep learning methods. 7 These methods are often difficult to adapt to aerial recognition tasks, which also have much room for development.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning to generalize aerial person re‐identification using the meta‐transfer method

Peng

Lü

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

Person re-identification (Re-ID) aims to retrieve a person of interest across multiple nonoverlapping cameras. In recent years, to enable person Re-ID technology to play out its application value in real-world scenarios, visual surveillance through unmanned aerial vehicle (UAV) platforms has received intense attention, and aerial person datasets have been constructed. However, the pedestrian images captured by ground cameras and those captured by UAVs exhibit great differences. Person Re-ID methods based on ground person images have difficulty performing Re-ID on aerial person images. In this paper, we first use a meta-transfer method to learn to gener-aerial imagery, meta-transfer learning, person re-identification

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to generalize aerial person re‐identification using the meta‐transfer method

Peng

Lü

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…A classical DASiS framework relies on either SYN-THIA (Ros et al, 2016) or GTA (Richter et al, 2016) dataset as a source, and the real-world Cityscapes (Cordts et al, 2016) dataset as a target. Some known exceptions include domain adaptation between medical images (Bermúdez-Chacón et al, 2018;Perone et al, 2019), aerial images (Lee et al, 2021), weather and seasonal condition changes of outdoor real images (Wulfmeier et al, 2017), and adaptation between different Field of View (FoV) images (Gu et al, 2021).…”

Section: Self-supervised Sismentioning

confidence: 99%

Semantic Image Segmentation: Two Decades of Research

Volpi¹,

Chidlovskii²

2022

View full text Add to dashboard Cite

Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning.State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this book is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends

show abstract

“…A classical DASiS framework relies on either SYNTHIA [154] or GTA [152] dataset as a source, and the real-world dataset Cityscapes [36] as a target. Some known exceptions include domain adaptation between medical images [7,147], aerial images [94], weather and seasonal conditions changes of outdoor real images [213], and different Field of View (FoV) images [64].…”

Section: Domain Adaptation For Semantic Image Segmentation (Dasis)mentioning

confidence: 99%

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey

Volpi¹,

Chidlovskii²

2021

Preprint

View full text Add to dashboard Cite

Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. Yet, the state-of-the-art models rely on large amount of annotated samples, which are more expensive to obtain than in tasks such as image classification. Since unlabelled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation reached a broad success within the semantic segmentation community.This survey is an effort to summarize five years of this incredibly rapidly growing field, which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning, domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research. We hope that this survey will provide researchers across academia and industry with a comprehensive reference guide and will help them in fostering new research directions in the field.1 See as example the https://github.com/errolPereira/ Semi-Automatic-Image-Annotation-Tool 2 We refer to the dedicated page https://github.com/ heartexlabs/awesome-data-labeling for an up-to-date collection of annotation tools.

show abstract

Self-Mutating Network for Domain Adaptive Segmentation of Aerial Images

Cited by 10 publications

References 31 publications

Learning to generalize aerial person re‐identification using the meta‐transfer method

Learning to generalize aerial person re‐identification using the meta‐transfer method

Semantic Image Segmentation: Two Decades of Research

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey

Contact Info

Product

Resources

About