Abstract
AbstractPooling operations, essential for neural networks, reduce feature map dimensions while preserving key features and enhancing spatial invariance. Traditional pooling methods often miss the feature maps' alternating currentcomponents. This study introduces a novel global pooling technique utilizing spectral self‐attention, leveraging the discrete cosine transform for spectral analysis and a self‐attention mechanism for assessing frequency component significance. This approach allows for efficient feature synthesis through weighted averaging, significantly boosting TOP‐1 accuracy with minimal parameter increase, outperforming existing models.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.