Domain adaption (DA) and domain generalization (DG) are two closely related methods which both concerned with the task of assigning labels to an unlabeled data set. The only dissimilarity between these approaches is that DA can access target during training phase, while totally unseen phase in DG. DG challenging as we have no earlier knowledge samples. If applied directly by a simple exclusion from training, poor performance will result for given task. In this paper, tackle challenge ways....

In the entire globe any educational organization is concerned in relation to attendance of individuals because this has an effect on their overall performances. conventional method students are taken by calling student names or signing paper which extremely time overwhelming. To eliminate problem one solutions a biometric-based system that can automatically capture students' recognizing iris. Iris recognition regarded as most reliable, accurate and efficient biometric identification due...

In this paper, microcontroller based automatic door open system has been developed. The is developed as speech recognition circuit where programmable voice used reference. Programmable means trained for identification of authorized and unauthorized person. As software part, MATLAB GUI interface to record voice, synthesize the recorded with feature extraction such power spectral density peak frequency by FFT (Fast Fourier Transform). Then these features will be verified every incoming voice....

Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of unlabeled domain. Generative adversarial networks (GANs) have demonstrated significant improvement in by producing images which are specific for training. However, most existing GAN based techniques unsupervised do not consider semantic information during matching, hence these methods degrade performance when data semantically different. In this paper, we...

The aim of this work is to develop a voice and Irish based automatic moving camera apply it in video conference where can save the cost as well reduce human involvements. This system has been divided into two main parts: software section hardware section. MATLAB data analyzing ARDUINO micro controller used for interfacing part with hardware. first records speaker detect maximum amplitude by using microphone then move help motor matching iris which have inputted before occurring conference.

Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the shift problem where distribution of source target data is different. The task DG more challenging than DA totally unseen during training phase in scenarios. current state-of-the-art employs adversarial techniques, however, these are rarely considered for problem. Furthermore, approaches do not consider correlation alignment which has been proven highly beneficial minimizing discrepancy. In this paper, we...

In this paper, we tackle the problem of training with multiple source domains aim to generalize new at test time without an adaptation step. This is known as domain generalization (DG). Previous works on DG assume identical categories or label space across domains. case category shift among domains, previous methods are vulnerable negative transfer due large mismatch spaces, decreasing target classification accuracy. To aforementioned problem, introduce end-to-end feature-norm network (FNN)...