Convolutional Neural Networks Quantization with Double-Stage Squeeze-and-Threshold

Article Computer Science, Information Systems

Hybrid attention network based on progressive embedding scale-context for crowd counting

Fusen Wang et al.

Summary: This paper proposes a hybrid attention network (HAN) that addresses background noise and head scale variation by incorporating progressive embedding scale context information. By building parallel spatial attention and channel attention modules and embedding scale-context in the network, the proposed method focuses on the human head area and reduces counting errors caused by perspective and head scale variation. A progressive learning strategy is introduced by cascading multiple hybrid attention modules to gradually integrate different scale-context information.

INFORMATION SCIENCES (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data

Min Zhao et al.

MEDICAL IMAGE ANALYSIS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

A Hybrid-Domain Deep Learning-Based BCI For Discriminating Hand Motion Planning From EEG Sources

Cosimo Ieracitano et al.

Summary: In this paper, a hybrid-domain deep learning approach is proposed to decode hand movement preparation phases from EEG recordings, achieving a significant performance improvement compared to temporal-only and time-frequency-only-based methods, with an average accuracy of 76.21 +/- 3.77%. By combining temporal and time-frequency information using two CNNs and a standard multi-layer perceptron, a better classification result is achieved.

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

MeliusNet: An Improved Network Architecture for Binary Neural Networks

Joseph Bethge et al.

Summary: This study introduces a binary neural network architecture MeliusNet, which alternates between a DenseBlock that increases feature capacity and an ImprovementBlock that enhances feature quality, demonstrating superior performance on the ImageNet dataset. MeliusNet achieves breakthroughs in computation savings and accuracy compared to other binary architectures, matching the accuracy level of the popular compact network MobileNet-v1.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021) (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

Zechun Liu et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2020)

Add to Collection

Article Biology

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals

U. Rajendra Acharya et al.

COMPUTERS IN BIOLOGY AND MEDICINE (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Deep Neural Networks for Acoustic Modeling in Speech Recognition

Geoffrey Hinton et al.

IEEE SIGNAL PROCESSING MAGAZINE (2012)

Add to Collection

Convolutional Neural Networks Quantization with Double-Stage Squeeze-and-Threshold

Related references

Hybrid attention network based on progressive embedding scale-context for crowd counting

An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data

A Hybrid-Domain Deep Learning-Based BCI For Discriminating Hand Motion Planning From EEG Sources

MeliusNet: An Improved Network Architecture for Binary Neural Networks

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals

Deep Neural Networks for Acoustic Modeling in Speech Recognition

Export Citation

Share Paper