When segmenting massive amounts of remote sensing images collected from different satellites or geographic locations (cities), the pre-trained deep learning models cannot always output satisfactory predictions. To deal with this issue, domain adaptation has been widely utilized to enhance the generalization abilities of the segmentation models. Most of the existing domain adaptation methods, which based on image-to-image translation, firstly transfer the source images to the pseudo-target images, adapt the classifier from the source domain to the target domain. However, these unidirectional methods suffer from the following two limitations: (1) they do not consider the inverse procedure and they cannot fully take advantage of the information from the other domain, which is also beneficial, as confirmed by our experiments; (2) these methods may fail in the cases where transferring the source images to the pseudo-target images is difficult. In this paper, in order to solve these problems, we propose a novel framework BiFDANet for unsupervised bidirectional domain adaptation in the semantic segmentation of remote sensing images. It optimizes the segmentation models in two opposite directions. In the source-to-target direction, BiFDANet learns to transfer the source images to the pseudo-target images and adapts the classifier to the target domain. In the opposite direction, BiFDANet transfers the target images to the pseudo-source images and optimizes the source classifier. At test stage, we make the best of the source classifier and the target classifier, which complement each other with a simple linear combination method, further improving the performance of our BiFDANet. Furthermore, we propose a new bidirectional semantic consistency loss for our BiFDANet to maintain the semantic consistency during the bidirectional image-to-image translation process. The experiments on two datasets including satellite images and aerial images demonstrate the superiority of our method against existing unidirectional methods.
In this paper, a large emotional speech database MASC (Mandarin affective speech corpus) is introduced. The database contains recordings of 68 native speakers (23 female and 45 male) and five kinds of emotional states: neutral, anger, elation, panic and sadness. Each speaker pronounces 5 phrases, 10 sentences for three times for each emotional states and 2 paragraphs only for neutral. These materials covers all the phonemes in Chinese. This corpus is constructed for prosodic and linguistic investigation of emotion expression in Mandarin. It can also be used for recognition of affectively stressed speakers. Furthermore, prosodic feature analysis and speaker recognition baseline experiment are performed on this database
10 March 2010 in Personal and Ubiquitous Computing
Rat cyborg is a rat which can receive cerebral commands and act as human wants. The navigation task is a widely used scenario in which the rat cyborg is required to walk along a specified path according to commands. Mostly the commands are given by human operators, but there's a need for automatic control which is quite challenging since several modules need to be elaborately combined together to work as a whole, among which the monitoring system and the commands model are two major components. Previously, few attempts were made for behavior monitoring of rat cyborg. Existing works often implement an over-simple rat information extractor which is capable of giving only a few parameters of the rat cyborg, which greatly limited the performance of their automatic control accuracy. In response to this requirement, we develop a monitoring system that is capable of giving detailed motion parameters and accurate body postures of the rat cyborg. We explore the possibility of recognizing rat postures using shape information, which is described by the powerful Zernike moments. We propose several simple shape descriptors which are fast to compute and achieve acceptable performance.
15 October 2014 in Journal of Zhejiang University SCIENCE C
The shapes of speakers’ vocal organs change under their different emotional states, which leads to the deviation of the emotional acoustic space of short-time features from the neutral acoustic space and thereby the degradation of the speaker recognition performance. Features deviating greatly from the neutral acoustic space are considered as mismatched features, and they negatively affect speaker recognition systems. Emotion variation produces different feature deformations for different phonemes, so it is reasonable to build a finer model to detect mismatched features under each phoneme. However, given the difficulty of phoneme recognition, three sorts of acoustic class recognition—phoneme classes, Gaussian mixture model (GMM) tokenizer, and probabilistic GMM tokenizer—are proposed to replace phoneme recognition. We propose feature pruning and feature regulation methods to process the mismatched features to improve speaker recognition performance. As for the feature regulation method, a strategy of maximizing the between-class distance and minimizing the within-class distance is adopted to train the transformation matrix to regulate the mismatched features. Experiments conducted on the Mandarin affective speech corpus (MASC) show that our feature pruning and feature regulation methods increase the identification rate (IR) by 3.64% and 6.77%, compared with the baseline GMM-UBM (universal background model) algorithm. Also, corresponding IR increases of 2.09% and 3.32% can be obtained with our methods when applied to the state-of-the-art algorithm i-vector.