Research map / Architectures and efficiency / CNN design
Deep Residual Learning in the JPEG Transform Domain
Max Ehrlich, Larry S. Davis
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| compute ReLu with Approximated Spatial Masking (ASM) instead of directly on the approximated block (APX) (ablation) | JPEG-domain ReLu · random 8x8 blocks, 1-15 spatial frequencies | RMSE | Improved |
| use ASM instead of APX ReLu in converted pretrained models (ablation) | JPEG-domain ResNet via model conversion · MNIST, CIFAR-10, CIFAR-100 | test accuracy | Improved |
| train in the JPEG domain rather than convert a spatial model, so fewer spatial frequencies suffice | JPEG-domain ResNet · MNIST, CIFAR-10, CIFAR-100 | test accuracy | Improved |
| operate on JPEG coefficients instead of decompressed images for inference | ResNet · MNIST, CIFAR-10, CIFAR-100 (NVIDIA Pascal GPU, batch 40) | inference throughput | Improved |
| operate on JPEG coefficients instead of decompressed images for training | ResNet · MNIST, CIFAR-10, CIFAR-100 (NVIDIA Pascal GPU, batch 40) | training throughput | Mixed |
Closest papers by meaning
- D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images (CVPR 2016 · similarity 0.88)
- JPEG Artifacts Reduction via Deep Convolutional Sparse Coding (ICCV 2019 · similarity 0.88)
- Learning Dual Priors for JPEG Compression Artifacts Removal (ICCV 2021 · similarity 0.88)
- Deep Residual Learning for Image Recognition (CVPR 2016 · similarity 0.88)
- End-to-end Optimized Image Compression (ICLR 2017 · similarity 0.88)
- RGB No More: Minimally-Decoded JPEG Vision Transformers (CVPR 2023 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
