paper-with-me

홈 › Papers

Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning

2020-10-19 · Hyunseung Chung, Woo-Jeoung Nam, Seong-Whan Lee

Remote sensing image retrieval (RSIR) is the process of ranking database images depending on the degree of similarity compared to the query image. As the complexity of RSIR increases due to the diversity in shooting range, angle, and location of remote sensors, there is an increasing demand for methods to address these issues and improve retrieval performance. In this work, we introduce a novel method for retrieving aerial images by merging group convolution with attention mechanism and metric learning, resulting in robustness to rotational variations. For refinement and emphasis on important features, we applied channel attention in each group convolution stage. By utilizing the characteristics of group convolution and channel-wise attention, it is possible to acknowledge the equality among rotated but identically located images. The training procedure has two main steps: (i) training the network with Aerial Image Dataset (AID) for classification, (ii) fine-tuning the network with triplet-loss for retrieval with Google Earth South Korea and NWPU-RESISC45 datasets. Results show that the proposed method performance exceeds other state-of-the-art retrieval methods in both rotated and original environments. Furthermore, we utilize class activation maps (CAM) to visualize the distinct difference of main features between our method and baseline, resulting in better adaptability in rotated environments.

📄 PDF Abstract BibTeX arXiv:2010.09202

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalMetric LearningRetrievalTriplet

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Few-Shot Rotation-Invariant Aerial Image Semantic Segmentation

2023-05-29 · Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang

Few-shot aerial image segmentation is a challenging task that involves precisely parsing objects in query aerial images with limited annotated support. Conventional matching methods without consideration of varying objec…

Image SegmentationSegmentationSemantic Segmentation

ReDet: A Rotation-equivariant Detector for Aerial Object Detection

2021-03-13 · CVPR 2021 1 · Jiaming Han, Jian Ding, Nan Xue, Gui-Song Xia

Recently, object detection in aerial images has gained much attention in computer vision. Different from objects in natural images, aerial objects are often distributed with arbitrary orientation. Therefore, the detector…

Objectobject-detectionObject DetectionObject Detection In Aerial Images

Rotation-Invariant Autoencoders for Signals on Spheres

2020-12-08 · Suhas Lohit, Shubhendu Trivedi

Omnidirectional images and spherical representations of $3D$ shapes cannot be processed with conventional 2D convolutional neural networks (CNNs) as the unwrapping leads to large distortion. Using fast implementations of…

ClusteringRetrieval

Rotation Invariant Deep CBIR

2020-06-21 · Subhadip Maji, Smarajit Bose

Introduction of Convolutional Neural Networks has improved results on almost every image-based problem and Content-Based Image Retrieval is not an exception. But the CNN features, being rotation invariant, creates proble…

Content-Based Image RetrievalDeep LearningImage RetrievalRetrieval

Compactification of the Rigid Motions Group in Image Processing

2021-06-25 · Tamir Bendory, Ido Hadi, Nir Sharon

Image processing problems in general, and in particular in the field of single-particle cryo-electron microscopy, often require considering images up to their rotations and translations. Such problems were tackled succes…