用可训练的JPEG压缩提升深度学习模型精度和抗攻击能力
JPEG Inspired Deep Learning
- 在DNN前加可训练的JPEG压缩层，通过可微软量化实现端到端优化
- 在多个数据集上准确率提升最高达20.9%，且增强对抗攻击鲁棒性
- 适合追求模型泛化性与轻量化部署的研究者和工程师
尽管传统观点认为有损图像压缩（如JPEG）会降低深度神经网络（DNN）性能，但近期研究显示，精心设计的JPEG压缩反而能提升深度学习表现。受此启发，我们提出JPEG-DL框架，在任意底层DNN架构前添加一个可训练的JPEG压缩层。为使JPEG中的量化操作可训练，引入新型可微软量化器，并与底层DNN联合优化。大量实验表明，相比标准深度学习，JPEG-DL在多个数据集和模型架构上均显著提升准确率，同时增强对对抗攻击的鲁棒性。尤其在某些细粒度图像分类数据集上，预测准确率最高提升20.9%。代码已开源：https://github.com/AhmedHussKhalifa/JPEG-Inspired-DL.git。
原文摘要 · Abstract (English)
Although it is traditionally believed that lossy image compression, such as JPEG compression, has a negative impact on the performance of deep neural networks (DNNs), it is shown by recent works that well-crafted JPEG compression can actually improve the performance of deep learning (DL). Inspired by this, we propose JPEG-DL, a novel DL framework that prepends any underlying DNN architecture with a trainable JPEG compression layer. To make the quantization operation in JPEG compression trainable, a new differentiable soft quantizer is employed at the JPEG layer, and then the quantization operation and underlying DNN are jointly trained. Extensive experiments show that in comparison with the standard DL, JPEG-DL delivers significant accuracy improvements across various datasets and model architectures while enhancing robustness against adversarial attacks. Particularly, on some fine-grained image classification datasets, JPEG-DL can increase prediction accuracy by as much as 20.9%. Our code is available on https://github.com/AhmedHussKhalifa/JPEG-Inspired-DL.git.
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。