.png){kind=icon}
返回
GOENet: Group Operations Enhanced Binary Neural Network for Efficient Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2024.3383796.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
There exists an innegligible performance gap between the binary neural networks and their full-precision counterparts, which prevents their deployment on real-world applications. Recently, plenty of researchers strive to solve this problem by incorporating more binary subnets, improving the representational power with acceptable complexity increase. However, current methods make structure design and parallel acceleration sophisticated and non-trivial and may degenerate the representational power due to the isomorphic subnets. Besides, the final feature fusion method is sub-optimal. In this letter, we propose a simple yet effective binary neural network named GOENet enhanced by group operations. The multiple parallel binary subnets use group-wise binary thresholds to improve feature diversity and are merged into the group convolutional layers. The inter-subnet connections are implemented with the parameter-free group shuffle operations, improving the model parallelism and performance. We also propose the group feature summation module as a better fusion method for its efficiency and effectiveness. Experimental results on ImageNet show that our proposed method outperforms the SOTA GroupNet by 1.7% Top-1 accuracy with 0.84x and 0.89x saving in computation and memory complexity.
Keyword:
Convolution
Neural networks
Training
Computational modeling
Memory management
Testing
Quantization (signal)
Binary neural networks
group operations
group subnets
group shuffle
group summation
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
A Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points一种基于心电图基准点的分层心律分类方法
OAAI
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏分享收藏
查看更多内容