用隐写技术做数据增强，提升图像分类训练效率
Steganographic Embeddings as an Effective Data Augmentation
- 用最小有效位隐写法嵌入秘密信息，生成新图像
- 在CIFAR-10上使训练效率显著提升，无需调参
- 隐写自带亮度/对比度等颜色变换，自动实现增广
图像隐写是一种密码学技术，将秘密信息嵌入图像中，使隐藏数据对人眼不可见且保持原图视觉完整性。最低有效位（LSB）隐写通过替换图像的k个最低有效位为秘密图像的k个最高有效位，既保留原图外观，又编码关键隐藏信息。本文突破传统应用，探索其在深度学习中的新用途：实验表明，将LSB隐写作为下游计算机视觉任务（如图像分类）的数据增强策略，可显著提升深度神经网络的训练效率。该方法还能以统一离散化的分段线性近似方式，隐式实现亮度、对比度、色相和饱和度等颜色增广，无需额外训练开销，且无需调节敏感的增广超参数，通过一种新的联合图像训练范式实现。
原文摘要 · Abstract (English)
Image Steganography is a cryptographic technique that embeds secret information into an image, ensuring the hidden data remains undetectable to the human eye while preserving the image's original visual integrity. Least Significant Bit (LSB) Steganography achieves this by replacing the k least significant bits of an image with the k most significant bits of a secret image, maintaining the appearance of the original image while simultaneously encoding the essential elements of the hidden data. In this work, we shift away from conventional applications of steganography in deep learning and explore its potential from a new angle. We present experimental results on CIFAR-10 showing that LSB Steganography, when used as a data augmentation strategy for downstream computer vision tasks such as image classification, can significantly improve the training efficiency of deep neural networks. It can also act as an implicit, uniformly discretized piecewise linear approximation of color augmentations such as (brightness, contrast, hue, and saturation), without introducing additional training overhead through a new joint image training regime that disregards the need for tuning sensitive augmentation hyperparameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。