基于自适应步幅卷积的细粒度视觉识别
FINE-GRAINED VISUAL CLASSIFICATION BASED ON ADAPTIVE STRIDE CONVOLUTION
谢毓广 1容圣海 2高博 1丁津津 1王子磊2
作者信息
- 1. 国网安徽省电力有限公司电力科学研究院 安徽 合肥 230601
- 2. 中国科学技术大学先进技术研究院 安徽 合肥 230000
- 折叠
摘要
平均池化等下采样方法已被广泛用于降低计算成本、防止过拟合和提高卷积神经网络的性能.然而,在细粒度的识别任务中,这些均匀采样方法不能很好地关注细微的辨别区域.提出一个自适应步幅卷积网络,其中自适应步幅卷积模块被用来专注于提取细微的特征.具体来说,给定一个图像,使用注意力图提取器获得一个注意力图,以突出物体的有判别性的部分.基于注意力图的步幅向量生成器产生步幅向量,它表示卷积核每次的移动步幅.自适应步幅卷积在输入图像上以不同的步幅提取信息.在CUB-200-2011、Stanford Cars和FGVC-Aircraft三个具有挑战性的细粒度数据集上,对该方法的有效性进行实验评估,结果达到先进的性能.
Abstract
Down-sampling methods such as average pooling have been widely used to reduce computation cost,prevent overfitting,and improve the performance of convolutional neural networks.However,in fine-grained recognition tasks,these uniform sampling methods cannot focus well on subtle discriminative regions.In this paper,we propose an Adaptive Stride Convolution Network(ASCNet)in which the ASC module is used to focus on extracting subtle features.Specifically,given an image,we obtained an attention map to highlight the discriminative parts of object,where the attention map extractor was used.The attention map-based stride generator produced stride vectors which indicated the moving steps of convolutional kernels every time.The adaptive stride convolution extracted information over the input image or features with varying strides.We experimentally evaluated the effectiveness of our method on three challenging fine-grained benchmarks,i.e.,CUB-200-2011,Stanford Cars,and FGVC-Aircraft,and advanced performance is achieved.
关键词
细粒度视觉识别/注意力机制/卷积/下采样/计算机视觉Key words
Fine-grained visual classification/Attention mechanism/Convolution/Down-sampling/Computer vision引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据