.png){kind=icon}
返回
Multiscale patch-based feature graphs for image classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2023.121116.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning architectures have demonstrated outstanding results in image classification in the last few years. However, applying sophisticated neural network architectures in small datasets remains challenging. In this context, transfer learning is a promising approach for dealing with this scenario. Generally, the available pre-trained architectures adopt a standard fixed input, which usually implies resizing and cropping the input images in the preprocessing phase, causing information loss. Besides, images present visual features in different scales in real-world scenarios, and most common approaches do not consider this fact. In this paper, we propose an approach that applies transfer learning for dealing with small datasets and leverages visual features extracted by pre-trained models from different scales. We based our approach on graph convolutional networks (GCN) that take graphs representing the images in different scales as input and whose nodes are characterized by features extracted by pre-trained models from regular image patches of different scales. Since GCN can deal with graphs with different numbers of nodes, our approach can deal naturally with images of heterogeneous sizes without discarding relevant information. We evaluated our approach in two datasets: a set of geological images and a publicly available dataset, both presenting characteristics that challenge traditional approaches. We tested our approach by adopting three different pre-trained models as feature extractors: two efficient pre-trained CNN models (DenseNet and ResNeXt) and one Vision Transformer (CLIP). We compared our approach with two conventional approaches for dealing with image classification. The experiments show that our approach achieves better results than the conventional approaches for this task.
Keyword:
Image classification
Transfer learning
Feature extraction
Multiscale
期刊
IF:
7.5
论文数:
3.0W
被引数:
12.7W
机构
引用论文
A New Approach to Polyp Detection by Pre-Processing of Images and Enhanced Faster R-CNN一种通过图像预处理和增强的Faster r-cnn进行息肉检测的新方法.png)
IEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
分享收藏COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data使用多模态成像数据通过迁移学习进行新型冠状病毒肺炎检测IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI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A Transfer Learning Evaluation of Deep Neural Networks for Image Classification面向图像分类的深度神经网络迁移学习评价
OAAI
OAAI分享收藏分享收藏Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network基于深度卷积神经网络的间质性肺疾病肺模式分类OAAI
OAAI分享收藏
查看更多内容