Compared with conventional zero-shot learning (ZSL), generalized ZSL (GZSL) is more challenging because the test instances may come from seen and unseen classes. The most existing GZSL methods learn a visual-semantic mapping function to bridge the knowledge transfer from seen to unseen classes by using semantic information and other labeled training data. However, these methods often suffer from severe performance degradation because they ignore similar structures between different classes.To solve these problems, we propose a GZSL method that transforms GZSL problems to conventional supervised learning ones by synthesizing pseudo features for unseen classes. This technique has two key aspects. The first one is the synthesis strategy; the proposed strategy directly synthesizes the pseudo features of unseen classes contrary to current synthesis-based methods, which synthesize pseudo instances. Our method regards the combination of N features of instances as the pseudo features. These N features belong to N different classes that are similar to unseen ones. This synthesis strategy is in line with the cognitive style of human beings. The second key aspect is that we preserve the similar structures between seen and unseen classes. Inspired by the center loss method, we assign each semantic vector as the center of deep features in the training stage. This way preserves the similar structures between the classes. Such preservation can be beneficial for improving classification accuracy. The experimental results on four benchmark datasets demonstrate that our model outperforms state-of-the-art methods for the GZSL. The source code is available at https://github.com/guizilaile23/SPF-GZSL.INDEX TERMS Generalized zero-shot learning, pseudo feature synthesis, image classification, supervised learning, multi-class classification.
When side-scan sonars collect data, sonar energy attenuation, the residual of time varying gain, beam patterns, angular responses, and sonar altitude variations occur, which lead to an uneven gray level in side-scan sonar images. Therefore, gray scale correction is needed before further processing of side-scan sonar images. In this paper, we introduce the causes of gray distortion in side-scan sonar images and the commonly used optical and side-scan sonar gray scale correction methods. As existing methods cannot effectively correct distortion, we propose a simple, yet effective gray scale correction method for side-scan sonar images based on Retinex given the characteristics of side-scan sonar images. Firstly, we smooth the original image and add a constant as an illumination map. Then, we divide the original image by the illumination map to produce the reflection map. Finally, we perform element-wise multiplication between the reflection map and a constant coefficient to produce the final enhanced image. Two different schemes are used to implement our algorithm. For gray scale correction of side-scan sonar images, the proposed method is more effective than the latest similar methods based on the Retinex theory, and the proposed method is faster. Experiments prove the validity of the proposed method.
Deep neural network (DNN) was applied in sonar image target recognition tasks, but it is very difficult to obtain enough sonar images that contain a target; as a result, the direct use of a small amount of data to train a DNN will cause overfitting and other problems. Transfer learning is the most effective way to address such scenarios. However, there is a large domain gap between optical images and sonar images, and common transfer learning methods may not be able to effectively handle it. In this paper, we propose a transfer learning method for sonar image classification and object detection called the texture feature removal network. We regard the texture features of an image as domain-specific features, and we narrow the domain gap by discarding the domain-specific features, and hence, make it easier to complete knowledge transfer. Our method can be easily embedded into other transfer learning methods, which makes it easier to apply to different application scenarios. Experimental results show that our method is effective in side-scan sonar image classification tasks and forward-looking sonar image detection tasks. For side-scan sonar image classification tasks, the classification accuracy of our method is enhanced by 4.5% in a supervised learning experiment, and for forward-looking sonar detection tasks, the average precision (AP) is also significantly improved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.