Steganographic Embeddings as an Effective Data Augmentation
This addresses the challenge of tuning sensitive augmentation hyperparameters for researchers and practitioners in computer vision, though it is incremental as it adapts an existing technique to a new application.
The paper tackled the problem of improving training efficiency for deep neural networks in computer vision by using Least Significant Bit Steganography as a data augmentation strategy, resulting in significant improvements on CIFAR-10 without additional training overhead.
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.