# Overcoming Scene Context Constraints for Object Detection in wild using Defilters

arXiv: https://arxiv.org/abs/2404.08293 · HTML: https://mlsanity.com/paper/2404.08293/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 10 references that are in the map.
- First posted on arXiv 12 Apr 2024.

## Builds on (most cited first, 9 of 9)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [MAXIM: Multi-Axis MLP for Image Processing](https://mlsanity.com/paper/2201.02973/) (2022)
- [A Robust Learning Approach to Domain Adaptive Object Detection](https://mlsanity.com/paper/1904.02361/) (2019)
- [Benchmarking performance of object detection under image distortions in an uncontrolled environment](https://mlsanity.com/paper/2210.15999/) (2022)

## Abstract (arXiv)

This paper focuses on improving object detection performance by addressing the issue of image distortions, commonly encountered in uncontrolled acquisition environments. High-level computer vision tasks such as object detection, recognition, and segmentation are particularly sensitive to image distortion. To address this issue, we propose a novel approach employing an image defilter to rectify image distortion prior to object detection. This method enhances object detection accuracy, as models perform optimally when trained on non-distorted images. Our experiments demonstrate that utilizing defiltered images significantly improves mean average precision compared to training object detection models on distorted images. Consequently, our proposed method offers considerable benefits for real-world applications plagued by image distortion. To our knowledge, the contribution lies in employing distortion-removal paradigm for object detection on images captured in natural settings. We achieved an improvement of 0.562 and 0.564 of mean Average precision on validation and test data.