DNN Flow: DNN Feature Pyramid based Image Matching
نویسندگان
چکیده
Figure 1: Matching I1 and I2 using DNN flow. Each column shows the matching of different levels. In first row, parallelogram denotes the DNN feature image of I1, where dot represents the feature at that location. Line with arrow denotes the flow vector of the corresponding feature, while curve with arrow denotes guidance from high level to low level. In second row, the color rectangles show I1’s patches covered by the DNN features. Third row shows I2’s matching patches corresponding to the patches of second row.
منابع مشابه
Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM
Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...
متن کاملHierarchical Neural Representation of Dreamed Objects Revealed by Brain Decoding with Deep Neural Network Features
Dreaming is generally thought to be generated by spontaneous brain activity during sleep with patterns common to waking experience. This view is supported by a recent study demonstrating that dreamed objects can be predicted from brain activity during sleep using statistical decoders trained with stimulus-induced brain activity. However, it remains unclear whether and how visual image features ...
متن کاملTowards Explanation of DNN-based Prediction with Guided Feature Inversion
While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics. Existing attempts based on local interpretations aim to identify relevant features contributing the most to the prediction of DNN by monitoring the neighborhood of...
متن کاملDeep neural network based trainable voice source model for synthesis of speech with varying vocal effort
This paper studies a deep neural network (DNN) based voice source modelling method in the synthesis of speech with varying vocal effort. The new trainable voice source model learns a mapping between the acoustic features and the time-domain pitch-synchronous glottal flow waveform using a DNN. The voice source model is trained with various speech material from breathy, normal, and Lombard speech...
متن کاملDeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework
As one of most fascinating machine learning techniques, deep neural network (DNN) has demonstrated excellent performance in various intelligent tasks such as image classification. DNN achieves such performance, to a large extent, by performing expensive trainings over huge volumes of training data. To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT...
متن کامل