Related papers: Efficient Attention Network: Accelerate Attention …
Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…
Human pose estimation is an essential yet challenging task in computer vision. One of the reasons for this difficulty is that there are many redundant regions in the images. In this work, we proposed a convolutional network architecture…
The process of training a deep neural network is characterized by significant time requirements and associated costs. Although researchers have made considerable progress in this area, further work is still required due to resource…
Deep Learning based techniques have gained significance over the past few years in the field of medicine. They are used in various applications such as classifying medical images, segmentation and identification. The existing architectures…
We propose a novel multi-task learning architecture, which allows learning of task-specific feature-level attention. Our design, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool,…
Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within…
This paper proposes SaleNet - an end-to-end convolutional neural network (CNN) for sustained attention level evaluation using prefrontal electroencephalogram (EEG). A bias-driven pruning method is proposed together with group convolution,…
Benefiting from the capability of building inter-dependencies among channels or spatial locations, attention mechanisms have been extensively studied and broadly used in a variety of computer vision tasks recently. In this paper, we…
Brain biometrics based on electroencephalography (EEG) have been used increasingly for personal identification. Traditional machine learning techniques as well as modern day deep learning methods have been applied with promising results. In…
Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accelerators has been proposed to accelerate the inference of…
Visual explanation is an approach for visualizing the grounds of judgment by deep learning, and it is possible to visually interpret the grounds of a judgment for a certain input by visualizing an attention map. As for deep-learning models…
The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…
The recurrent neural networks (RNN) can be used to solve the sequence to sequence problem, where both the input and the output have sequential structures. Usually there are some implicit relations between the structures. However, it is hard…
Traditional self-attention mechanisms in convolutional networks tend to use only the output of the previous layer as input to the attention network, such as SENet, CBAM, etc. In this paper, we propose a new attention modification method…
It has been shown that image descriptors extracted by convolutional neural networks (CNNs) achieve remarkable results for retrieval problems. In this paper, we apply attention mechanism to CNN, which aims at enhancing more relevant features…
Transformer-based architectures for speaker verification typically require more training data than ECAPA-TDNN. Therefore, recent work has generally been trained on VoxCeleb1&2. We propose a backbone network based on self-attention, which…
Transfer Learning enables Convolutional Neural Networks (CNN) to acquire knowledge from a source domain and transfer it to a target domain, where collecting large-scale annotated examples is time-consuming and expensive. Conventionally,…
Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…
Convolutional Neural Networks have achieved impressive results in various tasks, but interpreting the internal mechanism is a challenging problem. To tackle this problem, we exploit a multi-channel attention mechanism in feature space. Our…
Currently, convolutional neural networks (CNN) (e.g., U-Net) have become the de facto standard and attained immense success in medical image segmentation. However, as a downside, CNN based methods are a double-edged sword as they fail to…