Research map / Image generation / Autoregressive and latent generation
Deep Degradation Prior for Low-Quality Image Classification
Yang Wang, Yang Cao, Zheng-Jun Zha, Jing Zhang, Zhiwei Xiong
Check 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 |
|---|---|---|---|
| plug the FDM (deep degradation prior) into a pre-trained VGG16 trained on only 10 foggy CUB-C images | VGG16 · ImageNet-C fog | accuracy: 37% -> 55% | Improved |
| plug the FDM into VGG16 trained on 10 motion-blur images | VGG16 · ImageNet-C motion blur | accuracy: 24% -> 38% | Improved |
| reduce FDM training data from all 11788 images to 1% (ablation) | FDM · ImageNet-C Fog-3, Contrast-3, Brightness-3 | accuracy: drops by 5% | Hurt |
| use FDM instead of dehaze-then-classify two-stage methods | VGG16, AlexNet · ImageNet-C fog, 5 levels | accuracy: more than 30% | Improved |
| apply contrast-enhancement two-stage methods (HE, CVC, WAHE, LDR, OpenCE) before classifying | VGG16, AlexNet · ImageNet-C contrast levels 1-2 | accuracy | Hurt |
| use FDM instead of contrast enhancement | VGG16, AlexNet · ImageNet-C contrast, 5 levels | accuracy | Improved |
| apply HDR methods (LIME, HQEC, SRIE, MRINP) before classifying | VGG16, AlexNet · ImageNet-C brightness | accuracy | Hurt |
| use FDM instead of HDR enhancement | VGG16, AlexNet · ImageNet-C brightness | accuracy | Improved |
Closest papers by meaning
- Effects of Image Degradation and Degradation Removal to CNN-Based Image Classification (TPAMI 2019 · similarity 0.89)
- DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor (NeurIPS 2024 · similarity 0.89)
- Learning Degradation Representations for Image Deblurring (ECCV 2022 · similarity 0.87)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.85)
- Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks (CVPR 2025 · similarity 0.85)
- Universal Image Restoration Pre-training via Degradation Classification (ICLR 2025 · similarity 0.85)
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.
