A Few-Shot Learning Method for SAR Images Based on Weighted Distance and Feature Fusion
نویسندگان
چکیده
Convolutional Neural Network (CNN) has been widely applied in the field of synthetic aperture radar (SAR) image recognition. Nevertheless, CNN-based recognition methods usually encounter problem poor feature representation ability due to insufficient labeled SAR images. In addition, large inner-class variety and high cross-class similarity images pose a challenge for classification. To alleviate problems mentioned above, we propose novel few-shot learning (FSL) method recognition, which is composed multi-feature fusion network (MFFN) weighted distance classifier (WDC). The MFFN utilized extract input images’ features, WDC outputs classification results based on these features. constructed by adding multi-scale module (MsFFM) hand-crafted insertion (HcFIM) standard CNN. extraction capability can be enhanced inserting traditional features as auxiliary With aid information from different scales targets same class more easily aggregated. weight generation designed generate category-specific weights query distributes along corresponding Euclidean tackle problem. loss proposed improve performance guiding module. Experimental Moving Stationary Target Acquisition Recognition (MSTAR) dataset Vehicle Aircraft (VA) demonstrate that our surpasses several typical FSL methods.
منابع مشابه
Multi-Layer Model Based on Multi-Scale and Multi-Feature Fusion for SAR Images
A multi-layer classification approach based on multi-scales and multi-features (ML–MFM) for synthetic aperture radar (SAR) images is proposed in this paper. Firstly, the SAR image is partitioned into superpixels, which are local, coherent regions that preserve most of the characteristics necessary for extracting image information. Following this, a new sparse representation-based classification...
متن کاملDiscriminative Feature Learning from Sar Images
Clustering of Earth Observation (EO) images has gained a high amount of attention in remote sensing and data mining. Here, each image is represented by a high-dimensional feature vector which could be computed as the results of coding algorithms of extracted local descriptors or raw pixel values. In this work, we propose to learn the features using discriminative Nonnegative Matrix factorizatio...
متن کاملFew-shot Learning
Though deep neural networks have shown great success in the large data domain, they generally perform poorly on few-shot learning tasks, where a classifier has to quickly generalize after seeing very few examples from each class. The general belief is that gradient-based optimization in high capacity classifiers requires many iterative steps over many examples to perform well. Here, we propose ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2022
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs14184583