论文标题
Snapmix：以语义成比例混合以增强细粒度数据
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
论文作者
论文摘要
数据混合增强已被证明在培训深层模型中有效。最近的方法主要基于图像像素的混合比例混合标签。由于细粒图像的主要判别信息通常位于微妙的区域，因此沿着该线路的方法容易在细粒度识别中倾斜较重的标签噪声。我们在本文中提出了一种新型方案，称为语义上比例混合（Snapmix），该方案利用了类激活图（CAM）来减少标签噪声在增强细粒度数据中。 Snapmix通过估计其内在的语义组成来生成混合图像的目标标签，并允许不对称混合操作并确保合成图像和目标标签之间的语义对应关系。实验表明，我们的方法在各种数据集和不同网络深度下始终优于现有的基于混合的方法。此外，通过结合中级特征，提出的Snapmix实现了顶级性能，证明了其作为固体基线的潜力。我们的代码可在https://github.com/shaoli-huang/snapmix.git上找到。
Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in subtle regions, methods along this line are prone to heavy label noise in fine-grained recognition. We propose in this paper a novel scheme, termed as Semantically Proportional Mixing (SnapMix), which exploits class activation map (CAM) to lessen the label noise in augmenting fine-grained data. SnapMix generates the target label for a mixed image by estimating its intrinsic semantic composition, and allows for asymmetric mixing operations and ensures semantic correspondence between synthetic images and target labels. Experiments show that our method consistently outperforms existing mixed-based approaches on various datasets and under different network depths. Furthermore, by incorporating the mid-level features, the proposed SnapMix achieves top-level performance, demonstrating its potential to serve as a solid baseline for fine-grained recognition. Our code is available at https://github.com/Shaoli-Huang/SnapMix.git.
