Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Physical Sciences and Mathematics
Efficient Deep Neural Network Compression For Environmental Sound Classification On Microcontroller Units, Shan Chen, Na Meng, Haoyuan Li, Weiwei Fang
Efficient Deep Neural Network Compression For Environmental Sound Classification On Microcontroller Units, Shan Chen, Na Meng, Haoyuan Li, Weiwei Fang
Turkish Journal of Electrical Engineering and Computer Sciences
Environmental sound classification (ESC) is one of the important research topics within the non-speech audio classification field. While deep neural networks (DNNs) have achieved significant advances in ESC recently, their high computational and memory demands render them highly unsuitable for direct deployment on resource-constrained Internet of Things (IoT) devices based on microcontroller units (MCUs). To address this challenge, we propose a novel DNN compression framework specifically designed for such devices. On the one hand, we leverage pruning techniques to significantly compress the large number of model parameters in DNNs. To reduce the accuracy loss that follows pruning, we propose a …
Signer-Independent Sign Language Recognition With Feature Disentanglement, İnci̇ Meli̇ha Baytaş, İpek Erdoğan
Signer-Independent Sign Language Recognition With Feature Disentanglement, İnci̇ Meli̇ha Baytaş, İpek Erdoğan
Turkish Journal of Electrical Engineering and Computer Sciences
Learning a robust and invariant representation of various unwanted factors in sign language recognition (SLR) applications is essential. One of the factors that might degrade the sign recognition performance is the lack of signer diversity in the training datasets, causing a dependence on the singer’s identity during representation learning. Consequently, capturing signer-specific features hinders the generalizability of SLR systems. This study proposes a feature disentanglement framework comprising a convolutional neural network (CNN) and a long short-term memory (LSTM) network based on adversarial training to learn a signer-independent sign language representation that might enhance the recognition of signs. We aim to …
Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu
Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu
Turkish Journal of Electrical Engineering and Computer Sciences
Domain generalization (DG) techniques strive to attain the ability to generalize to an unfamiliar target domain solely based on training data originating from the source domains. Despite the increasing attention given to learning from multiple training domains through the application of various forms of invariance across those domains, the enhancements observed in comparison to ERM are nearly insignificant under specified evaluation rules. In this paper, we demonstrate that the disentanglement of spurious and invariant features is a challenging task in conventional training since ERM simply minimizes the loss and does not exploit invariance among domains. To address this issue, we …