mlsanityData to 7 Oct 2026

JPEG Inspired Deep Learning

arXiv 2410.07081 ↗First posted 9 Oct 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

28 of 43 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  10. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  11. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  12. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
16 more
  1. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  2. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  3. 2019Contrastive Representation Distillationcited by 734
  4. 2016End-to-end Optimized Image Compressioncited by 673
  5. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  6. 2019Learned Step Size Quantizationcited by 604
  7. 2017Countering Adversarial Images using Input Transformationscited by 517
  8. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  9. 2016A study of the effect of JPG compression on adversarial imagescited by 196
  10. 2020Regularizing Class-wise Predictions via Self-knowledge Distillationcited by 144
  11. 2016Understanding How Image Quality Affects Deep Neural Networkscited by 118
  12. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
  13. 2023Initializing Models with Larger Onescited by 39
  14. 2018DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Frameworkcited by 23
  15. 2020The Rate-Distortion-Accuracy Tradeoff: JPEG Case Studycited by 22
  16. 2023MULLER: Multilayer Laplacian Resizer for Visioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Diffusion-based Cumulative Adversarial Purification for Vision Language Modelscited by 2
  2. 2025Raw-JPEG Adapter: Efficient Raw Image Compression with JPEGcited by 0
  3. 2026Learned JPEG Compression for DNN Visioncited by 0