GlanceNets — efficient convolutional neural networks with adaptive hard example mining
نویسندگان
چکیده
منابع مشابه
Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining
Detecting vehicles in aerial imagery plays an important role in a wide range of applications. The current vehicle detection methods are mostly based on sliding-window search and handcrafted or shallow-learning-based features, having limited description capability and heavy computational costs. Recently, due to the powerful feature representations, region convolutional neural networks (CNN) base...
متن کاملAirport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining
Deep convolutional neural network (CNN) achieves outstanding performance in the field of target detection. As one of the most typical targets in remote sensing images (RSIs), airport has attracted increasing attention in recent years. However, the essential challenge for using deep CNN to detect airport is the great imbalance between the number of airports and background examples in large-scale...
متن کاملAdaptive Graph Convolutional Neural Networks
Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking dat...
متن کاملText Mining with Adaptive Neural Networks
Analysing high-dimensional data is a task where software tools can reasonably assist the data analyst, by visualising, and thereby uncovering, the inherent structure and topology of the data collection. Especially the kinds of tools that can produce results autonomously, i.e. unsupervised tools, are a goal; here, neural network models may be one solution. In the category of unsupervised neural ...
متن کاملEfficient Sparse-Winograd Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are compute intensive which limits their application on mobile devices. Their energy is dominated by the number of multiplies needed to perform the convolutions. Winograd’s minimal filtering algorithm (Lavin (2015)) and network pruning (Han et al. (2015)) reduce the operation count. Unfortunately, these two methods cannot be combined — because applying the W...
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: Science China Information Sciences
سال: 2018
ISSN: 1674-733X,1869-1919
DOI: 10.1007/s11432-018-9497-0