.png){kind=icon}
返回
Hierarchical neural network with efficient selection inference
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2023.02.015.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The image classification precision is vastly enhanced with the growing complexity of convolutional neural network (CNN) structures. However, the uneven visual separability between categories leads to various difficulties in classification. The hierarchical structure of categories can be leveraged to deal with it, but a few CNNs pay attention to the character of data. Besides, a network model with a hierarchical structure is promising to extract more specific features from the data than current CNNs, since, for the latter, all categories have the same fixed number of layers for feed-forward computation. In this paper, we propose to use category hierarchies to integrate ResNet-style modules to form a hierarchical network model in a top-down manner. To extract abundant discriminative features and improve the computation efficiency, we adopt residual block selection based on coarse categories to allocate different computation paths. Each residual block works as a switch to determine the JUMP or JOIN mode for an individual coarse category. Interestingly, since some categories need less feedforward computation than others by jumping layers, the average inference time cost is reduced. Extensive experiments show that our hierarchical network achieves higher prediction accuracy with similar FLOPs on CIFAR-10 and CIFAR-100, SVHM, and Tiny-ImageNet datasets compared to original residual networks and other existing selection inference methods. (c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Convolutional neural network (CNN)
Image classification
Category hierarchy
Dynamic computation
Path decision search
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Multiple convolutional layers fusion framework for hyperspectral image classification用于高光谱图像分类的多卷积层融合框架.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
PREAI
分享收藏分享收藏Feature Selection-Based Hierarchical Deep Network for Image Classification基于特征选择的分层深度网络图像分类IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Effect of Oil Massage on Growth in Preterm Neonates Less than 1800 g: A Randomized Control Trial
PREAI
分享收藏分享收藏
查看更多内容