融合显著性和非局部模块的细粒度图像分类算法
Fine-grained image classification algorithm combining saliency and non-local module
凌晨 1张荣福 1杨紫叶 1高顾昱 1赵富强1
作者信息
- 1. 上海理工大学 光电信息与计算机工程学院,上海 200093
- 折叠
摘要
针对细粒度图像分类任务中存在鉴别性特征获取不准确和训练数据利用不充分的问题,提出了融合显著性和非局部模块的细粒度图像分类算法.通过裁剪 4 张训练图像的显著性区域将其拼接为 1 张训练图像来丰富和增强训练数据,并将非局部模块嵌入到ResNet-50 模型高维特征层中的瓶颈模块中来联系所增强图像的 4 个显著性区域,以加强模型对全局上下文信息的关注.在Stanford Cars和CUB-200-2011 数据集上,Top-1 分类准确率分别达到了 94.01%和 85.97%.与数据增强方法和细粒度图像分类算法相比,本方法性能更优.
Abstract
Aiming at the problems of inaccurate discriminative feature acquisition and insufficient use of training data in fine-grained image classification tasks,a fine-grained image classification algorithm combining significance and non-local modules is proposed.By clipping the significance region of four training images and stitching them into one training image,the training data could be enriched and enhanced.Moreover,the non-local module was embedded into the bottleneck module in the high-dimensional feature layer of the ResNet-50 model to connect the four salience regions of the enhanced image,which strengthened the model's attention to the global context information.On the Stanford Cars and CUB-200-2011 data sets,the accuracy of Top-1 classification was 94.01%and 85.97%,respectively.This method performs better than compared data augmentation methods and fine-grained image classification algorithms.
关键词
细粒度图像分类/显著性/数据增强/深度学习Key words
fine-grained image classification/saliency/data augmentation/deep learning引用本文复制引用
出版年
2024
NETL
NSTL
万方数据