2019/07/19 by Yingwei Zhou, Zhou, Yingwei · 1 citation
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Deep learning #Deep neural networks #FOS: Computer and information sciences #FOS: Electrical engineering #Feature (linguistics) #Flexibility (engineering) #Focus (optics) #Image (mathematics) #Image and Video Processing (eess.IV) #Image segmentation #Machine Learning (cs.LG) #Machine learning #Object (grammar) #Object detection #Pattern recognition (psychology) #Segmentation #Video Surveillance and Tracking Methods #cs.CV #cs.LG #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1907.12900
published in arXiv (Cornell University) (Cornell University) · preprint draft
arxiv created 2019/07/19 · openalex publication_date 2019/07/19 · arxiv updated 2019/07/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as instance segmentation, video tracking and robotic vision. As the core concept of Deep Learning, Deep Neural Networks (DNNs) and associated training are highly integrated with task-driven modelling, having great effects on accurate detection. The main focus of improving detection performance is proposing DNNs with extra layers and novel topological connections to extract the desired features from input data. However, training these models can be computationally expensive and laborious progress as the complicated model architecture and enormous parameters. Besides, the dataset is another reason causing this issue and low detection accuracy, because of insufficient data samples or difficult instances. To address these training difficulties, this thesis presents two different approaches to improve the detection performance in the relatively light-weight way. As the intrinsic feature of data-driven in deep learning, the first approach is "slot-based image augmentation" to enrich the dataset with extra foreground and background combinations. Instead of the commonly used image flipping method, the proposed system achieved similar mAP improvement with less extra images which decrease training time. This proposed augmentation system has extra flexibility adapting to various scenarios and the performance-driven analysis provides an alternative aspect of conducting image augmentation