论文标题
具有自适应类激活映射的多视图功能增强
Multi-view Feature Augmentation with Adaptive Class Activation Mapping
论文作者
论文摘要
我们提出了一个用于图像分类的端到端可训练的功能增强模块，该模块提取和利用多视图本地功能来增强模型性能。不同于使用全球平均池（GAP）仅从全局视图中提取矢量化特征，我们建议采样和集成多样的多视图本地特征，以提高模型鲁棒性。为了示例班级代表性的本地特征，我们合并了一个简单的辅助分类器头（仅包含1 $ \ times $ 1的卷积层），通过我们建议的Adacam（适应性的班级激活映射映射），有效地适应了特征图的类歧视局部特征图的本地区域。广泛的实验表明，我们的多视图功能增强模块获得了一致且明显的性能提高。
We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized features from only the global view, we propose to sample and ensemble diverse multi-view local features to improve model robustness. To sample class-representative local features, we incorporate a simple auxiliary classifier head (comprising only one 1$\times$1 convolutional layer) which efficiently and adaptively attends to class-discriminative local regions of feature maps via our proposed AdaCAM (Adaptive Class Activation Mapping). Extensive experiments demonstrate consistent and noticeable performance gains achieved by our multi-view feature augmentation module.
