Search

Conventional deep neural networks face challenges in handling the increasing amount of information in real-world scenarios where it is impractical to gather all the training data at once. Incremental learning, also known as continual learning, provides a solution for lightweight and sustainable learning with neural networks. However, incremental learning encounters issues such as "catastrophic forgetting" and the "stability–plasticity dilemma". To address these challenges, this study proposes a two-stage training method. In the first stage, dual knowledge distillation is introduced, including feature map-based and response-based knowledge distillation. This approach prevents the model from excessively favoring new tasks during training, thus addressing catastrophic forgetting. In the second stage, an out-of-distribution dataset is incorporated to calculate the discrepancy loss between multiple classifiers. By maximizing the discrepancy loss and minimizing the cross-entropy loss, the model improves the classification accuracy of new tasks. The proposed method is evaluated using the CIFAR100 and RESISC45 benchmark datasets, comparing it to existing approaches. Experimental results demonstrate an overall accuracy improvement of 6.9% and a reduction of 5.1% in the forgetting rate after adding nine consecutive tasks. These findings indicate that the proposed method effectively mitigates catastrophic forgetting and provides a viable solution for image classification in natural and remote sensing images. [ABSTRACT FROM AUTHOR]

Video action recognition is vital in the research area of computer vision. In this paper, we develop a novel model, named Separable ConvNet Spatiotemporal Mixer (SCSM). Our goal is to develop an efficient and lightweight action recognition backbone that can be applied to multi-task models to increase the accuracy and processing speed. The SCSM model uses a new hierarchical spatial compression, employing the spatiotemporal fusion method, consisting of a spatial domain and a temporal domain. The SCSM model maintains the independence of each frame in the spatial domain for feature extraction and fuses the spatiotemporal features in the temporal domain. The architecture can be adapted to different frame rate requirements due to its high scalability. It is suitable to serve as a backbone for multi-task video feature extraction or industrial applications with its low prediction and training costs. According to the experimental results, SCSM has a low number of parameters and low computational complexity, making it highly scalable with strong transfer learning capabilities. The model achieves video action recognition accuracy comparable to state-of-the-art models with a smaller parameter size and fewer computational requirements. [ABSTRACT FROM AUTHOR]

This paper presents a system applied to unmanned aerial vehicles based on Robot Operating Systems (ROSs). The study addresses the challenges of efficient object detection and real-time target tracking for unmanned aerial vehicles. The system utilizes a pruned YOLOv4 architecture for fast object detection and the SiamMask model for continuous target tracking. A Proportional Integral Derivative (PID) module adjusts the flight attitude, enabling stable target tracking automatically in indoor and outdoor environments. The contributions of this work include exploring the feasibility of pruning existing models systematically to construct a real-time detection and tracking system for drone control with very limited computational resources. Experiments validate the system's feasibility, demonstrating efficient object detection, accurate target tracking, and effective attitude control. This ROS-based system contributes to advancing UAV technology in real-world environments. [ABSTRACT FROM AUTHOR]

This paper presents a framework that can automatically analyze the images and comments in user-uploaded location databases. The proposed framework integrates image processing and natural language processing techniques to perform scene classification, data cleaning, and comment summarization so that the cluttered information in user-uploaded databases can be presented in an organized way to users. For scene classification, RGB image features, segmentation features, and the features of discriminative objects are fused with an attention module to improve classification accuracy. For data cleaning, incorrect images are detected using a multilevel feature extractor and a multiresolution distance calculation scheme. Finally, a comment summarization scheme is proposed to overcome the problems of unstructured sentences and the improper usage of punctuation marks, which are commonly found in customer reviews. To validate the proposed framework, a system that can classify and organize scenes and comments for hotels is implemented and evaluated. Comparisons with existing related studies are also performed. The experimental results validate the effectiveness and superiority of the proposed framework. [ABSTRACT FROM AUTHOR]