Toàn Phạm Văn

Toan Pham Van, Linh Bao Doan, Thanh Tung Nguyen et al.

Semantic segmentation is an essential task in developing medical image diagnosis systems. However, building an annotated medical dataset is expensive. Thus, semi-supervised methods are significant in this circumstance. In semi-supervised learning, the quality of labels plays a crucial role in model performance. In this work, we present a new pseudo labeling strategy that enhances the quality of pseudo labels used for training student networks. We follow the multi-stage semi-supervised training approach, which trains a teacher model on a labeled dataset and then uses the trained teacher to render pseudo labels for student training. By doing so, the pseudo labels will be updated and more precise as training progress. The key difference between previous and our methods is that we update the teacher model during the student training process. So the quality of pseudo labels is improved during the student training process. We also propose a simple but effective strategy to enhance the quality of pseudo labels using a momentum model -- a slow copy version of the original model during training. By applying the momentum model combined with re-rendering pseudo labels during student training, we achieved an average of 84.1% Dice Score on five datasets (i.e., Kvarsir, CVC-ClinicDB, ETIS-LaribPolypDB, CVC-ColonDB, and CVC-300) with only 20% of the dataset used as labeled data. Our results surpass common practice by 3% and even approach fully-supervised results on some datasets. Our source code and pre-trained models are available at https://github.com/sun-asterisk-research/online learning ssl

Toan Pham Van, Son Trung Nguyen, Linh Bao Doan et al.

Many cultures around the world believe that palm reading can be used to predict the future life of a person. Palmistry uses features of the hand such as palm lines, hand shape, or fingertip position. However, the research on palm-line detection is still scarce, many of them applied traditional image processing techniques. In most real-world scenarios, images usually are not in well-conditioned, causing these methods to severely under-perform. In this paper, we propose an algorithm to extract principle palm lines from an image of a person's hand. Our method applies deep learning networks (DNNs) to improve performance. Another challenge of this problem is the lack of training data. To deal with this issue, we handcrafted a dataset from scratch. From this dataset, we compare the performance of readily available methods with ours. Furthermore, based on the UNet segmentation neural network architecture and the knowledge of attention mechanism, we propose a highly efficient architecture to detect palm-lines. We proposed the Context Fusion Module to capture the most important context feature, which aims to improve segmentation accuracy. The experimental results show that it outperforms the other methods with the highest F1 Score about 99.42% and mIoU is 0.584 for the same dataset.

Toan Pham Van, Ngoc N. Tran, Ta Minh Thanh

Singer voice classification is a meaningful task in the digital era. With a huge number of songs today, identifying a singer is very helpful for music information retrieval, music properties indexing, and so on. In this paper, we propose a new method to identify the singer's name based on analysis of Vietnamese popular music. We employ the use of vocal segment detection and singing voice separation as the pre-processing steps. The purpose of these steps is to extract the singer's voice from the mixture sound. In order to build a singer classifier, we propose a neural network architecture working with Mel Frequency Cepstral Coefficient as extracted input features from said vocal. To verify the accuracy of our methods, we evaluate on a dataset of 300 Vietnamese songs from 18 famous singers. We achieve an accuracy of 92.84% with 5-fold stratified cross-validation, the best result compared to other methods on the same data set.

Quang Pham Huu, Thoi Hoang Dinh, Ngoc N. Tran et al.

In the last few years, steganography has attracted increasing attention from a large number of researchers since its applications are expanding further than just the field of information security. The most traditional method is based on digital signal processing, such as least significant bit encoding. Recently, there have been some new approaches employing deep learning to address the problem of steganography. However, most of the existing approaches are designed for image-in-image steganography. In this paper, the use of deep learning techniques to hide secret audio into the digital images is proposed. We employ a joint deep neural network architecture consisting of two sub-models: the first network hides the secret audio into an image, and the second one is responsible for decoding the image to obtain the original audio. Extensive experiments are conducted with a set of 24K images and the VIVOS Corpus audio dataset. Through experimental results, it can be seen that our method is more effective than traditional approaches. The integrity of both image and audio is well preserved, while the maximum length of the hidden audio is significantly improved.