☆ 4.6 Article

Convolutional neural network optimization via channel reassessment attention module

DIGITAL SIGNAL PROCESSING (2022)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

Structural pixel-wise target attention for robust object tracking

Huanlong Zhang et al.

Summary: This study introduces a structural pixel-wise target attention model for robust object tracking, combined with a memory model to provide high-quality training samples for updates. The experimental results show that the method adapts to target variations, prevents background noise, and improves model discriminability.

DIGITAL SIGNAL PROCESSING (2021)

Add to Collection

Article Engineering, Electrical & Electronic

A new CNN training approach with application to hyperspectral image classification

Sezer Kutluk et al.

Summary: The paper focuses on proposing a new training algorithm for convolutional neural networks that utilizes both first and second order derivatives to achieve higher classification accuracy in fewer training iterations. The approach not only trains faster in terms of the number of iterations, but also in training duration, showing superior results compared to existing methods.

DIGITAL SIGNAL PROCESSING (2021)

Add to Collection

Article Engineering, Electrical & Electronic

EffCDNet: Transfer learning with deep attention network for change detection in high spatial resolution satellite images

Parmeshwar S. Patil et al.

Summary: This study presents an efficient algorithm for change detection using high spatial resolution satellite images. The algorithm combines deep learning techniques and optimized convolutional neural networks, utilizing attention mechanisms and fusion techniques to achieve more accurate and faster change detection. It is significant for improving segmentation performance and enhancing the representation of detail maps.

DIGITAL SIGNAL PROCESSING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inference

Jian-Hao Luo et al.

PATTERN RECOGNITION (2020)

Add to Collection

Convolutional neural network optimization via channel reassessment attention module

Related references

Structural pixel-wise target attention for robust object tracking

A new CNN training approach with application to hyperspectral image classification

EffCDNet: Transfer learning with deep attention network for change detection in high spatial resolution satellite images

AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inference

Export Citation

Share Paper