# RestoreX-AI: A Contrastive Approach towards Guiding Image Restoration via Explainable AI Systems

arXiv: https://arxiv.org/abs/2204.01719 · HTML: https://mlsanity.com/paper/2204.01719/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 22 of 22)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://mlsanity.com/paper/1712.02294/) (2017)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/1910.06528/) (2019)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [Interpreting Black Box Predictions using Fisher Kernels](https://mlsanity.com/paper/1810.10118/) (2018)
- [DAWN: Vehicle Detection in Adverse Weather Nature Dataset](https://mlsanity.com/paper/2008.05402/) (2020)
- [Adversarial Training for Adverse Conditions: Robust Metric Localisation using Appearance Transfer](https://mlsanity.com/paper/1803.03341/) (2018)
- [I Can See Clearly Now : Image Restoration via De-Raining](https://mlsanity.com/paper/1901.00893/) (2019)
- [Benchmarking Image Sensors Under Adverse Weather Conditions for Autonomous Driving](https://mlsanity.com/paper/1912.03238/) (2019)
- [MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views](https://mlsanity.com/paper/2006.05518/) (2020)

## Built on by (most cited first, 9 of 9)

- [UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2205.01871/) (2022)
- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)
- [Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?](https://mlsanity.com/paper/2312.04548/) (2023)
- [Residual Diffusion Bridge Model for Image Restoration](https://mlsanity.com/paper/2510.23116/) (2025)
- [DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration](https://mlsanity.com/paper/2504.21487/) (2025)
- [t-RAIN: Robust generalization under weather-aliasing label shift attacks](https://mlsanity.com/paper/2305.08302/) (2023)
- [Hierarchical-level rain image generative model based on GAN](https://mlsanity.com/paper/2309.02964/) (2023)
- [Dual-Integrated Low-Latency Single-Lens Infrared Computational Imaging for Object Detection](https://mlsanity.com/paper/2605.21964/) (2026)
- [Task-Sensitive Geometry of Representation Transfer for Object Detection under Image Degradation](https://mlsanity.com/paper/2610.04627/) (2026)

## Abstract (arXiv)

Modern applications such as self-driving cars and drones rely heavily upon robust object detection techniques. However, weather corruptions can hinder the object detectability and pose a serious threat to their navigation and reliability. Thus, there is a need for efficient denoising, deraining, and restoration techniques. Generative adversarial networks and transformers have been widely adopted for image restoration. However, the training of these methods is often unstable and time-consuming. Furthermore, when used for object detection (OD), the output images generated by these methods may provide unsatisfactory results despite image clarity. In this work, we propose a contrastive approach towards mitigating this problem, by evaluating images generated by restoration models during and post training. This approach leverages OD scores combined with attention maps for predicting the usefulness of restored images for the OD task. We conduct experiments using two novel use-cases of conditional GANs and two transformer methods that probe the robustness of the proposed approach on multi-weather corruptions in the OD task. Our approach achieves an averaged 178 percent increase in mAP between the input and restored images under adverse weather conditions like dust tornadoes and snowfall. We report unique cases where greater denoising does not improve OD performance and conversely where noisy generated images demonstrate good results. We conclude the need for explainability frameworks to bridge the gap between human and machine perception, especially in the context of robust object detection for autonomous vehicles.