.png){kind=icon}
返回
Alignable kernel network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.inffus.2024.102758.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
To enhance the adaptability and performance of Convolutional Neural Networks (CNN), we present an adaptable mechanism called Alignable Kernel (AliK) unit, which dynamically adjusts the receptive field (RF) dimensions of a model in response to varying stimuli. The branches of AliK unit are integrated through a novel align transformation softmax attention, incorporating prior knowledge through rank ordering constraints. The attention weightings across the branches establish the effective RF scales, leveraged by neurons in the fusion layer. This mechanism is inspired by neuroscientific observations indicating that the RF dimensions of neurons in the visual cortex vary with the stimulus, a feature often overlooked in CNN architectures. By aggregating successive AliK ensembles, we develop a deep network architecture named the Alignable Kernel Network (AliKNet). AliKNet with interdisciplinary design improves the network's performance and interpretability by taking direct inspiration from the structure and function of human neural systems, especially the visual cortex. Empirical evaluations in the domains of image classification and semantic segmentation have demonstrated that AliKNet excels over numerous state-of-the-art architectures, achieving this without increasing model complexity. Furthermore, we demonstrate that AliKNet can identify target objects across various scales, confirming their ability to dynamically adapt their RF sizes in response to the input data.
Keyword:
CNN
Receptive field
Neural network
Alignable kernel network
期刊
IF:
15.5
论文数:
4.2K
被引数:
2.7W
机构
引用论文
分享收藏分享收藏
分享收藏Model-Assisted Multi-source Fusion Hypergraph Convolutional Neural Networks for intelligent few-shot fault diagnosis to Electro-Hydrostatic Actuator.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏
查看更多内容