Research map / Detection and segmentation / Open-set and few-shot detection
Rethinking Image Restoration for Object Detection
Shangquan Sun, Wenqi Ren, Tao Wang, Xiaochun Cao
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 |
|---|---|---|---|
| use ADAM-based targeted attack instead of TOG to generate perturbation (ablation) | targeted adversarial attack · RTTS (YOLOv3) | mAP: 71.98 -> 78.50 | Improved |
| fine-tune restoration with our attacked pseudo ground truth vs conventional training | MSBDN · VOC_fog_test (YOLOv3) | mAP: 77.06 -> 77.66 | Improved |
| fine-tune restoration with our attacked pseudo ground truth vs conventional training | GridDehaze · VOC_fog_test (YOLOv3) | mAP: 69.29 -> 78.36 | Improved |
| fine-tune restoration with our pseudo ground truth vs conventional training | MSBDN · RTTS (YOLOv3) | mAP: 43.87 -> 44.10 | Improved |
| fine-tune restoration with our pseudo ground truth vs conventional training | SCI · ExDark (YOLOv3) | mAP: 48.47 -> 48.59 | Improved |
| fine-tune ZeroDCE with our pseudo ground truth vs conventional training | ZeroDCE · ExDark (YOLOv3) | mAP: 41.01 -> 41.21 | No clear effect |
| fine-tune restoration with attacked pseudo-GT | dehazing / low-light models · PSNR/SSIM | PSNR: 28.72 -> 28.53 | Mixed |
| learning restoration from attacked pseudo-GT vs directly attacking test images | restoration models · RTTS | mAP: 78.50 -> 44.10 | Hurt |
Closest papers by meaning
- Towards Adversarially Robust Object Detection (ICCV 2019 · similarity 0.86)
- Adversarially-Aware Robust Object Detector (ECCV 2022 · similarity 0.86)
- Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search (ICML 2018 · similarity 0.85)
- Physics-Based Generative Adversarial Models for Image Restoration and Beyond (TPAMI 2020 · similarity 0.85)
- Transferable Adversarial Attacks for Object Detection Using Object-Aware Significant Feature Distortion (AAAI 2024 · similarity 0.85)
- Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy (NeurIPS 2025 · similarity 0.83)
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.
