# Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks

arXiv: https://arxiv.org/abs/2103.05889 · HTML: https://mlsanity.com/paper/2103.05889/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 10 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Learning Data Augmentation Strategies for Object Detection](https://mlsanity.com/paper/1906.11172/) (2019)
- [Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation](https://mlsanity.com/paper/1906.02611/) (2019)
- [Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy](https://mlsanity.com/paper/2004.00448/) (2020)
- [Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond](https://mlsanity.com/paper/1811.02545/) (2018)
- [Towards Domain Invariant Single Image Dehazing](https://mlsanity.com/paper/2101.10449/) (2021)
- [NTIRE 2020 Challenge on Image Demoireing: Methods and Results](https://mlsanity.com/paper/2005.03155/) (2020)

## Built on by (most cited first, 4 of 4)

- [Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation](https://mlsanity.com/paper/2506.16802/) (2025)
- [DGSS : Domain Generalized Semantic Segmentation using Iterative Style Mining and Latent Representation Alignment](https://mlsanity.com/paper/2202.13144/) (2022)
- [DAMix: A Density-Aware Mixup Augmentation for Single Image Dehazing under Domain Shift](https://mlsanity.com/paper/2109.12544/) (2021)
- [Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks](https://mlsanity.com/paper/2204.01795/) (2022)

## Abstract (arXiv)

Region modification-based data augmentation techniques have shown to improve performance for high level vision tasks (object detection, semantic segmentation, image classification, etc.) by encouraging underlying algorithms to focus on multiple discriminative features. However, as these techniques destroy spatial relationship with neighboring regions, performance can be deteriorated when using them to train algorithms designed for low level vision tasks (low light image enhancement, image dehazing, deblurring, etc.) where textural consistency between recovered and its neighboring regions is important to ensure effective performance. In this paper, we examine the efficacy of a simple copy-blend data augmentation technique that copies patches from noisy images and blends onto a clean image and vice versa to ensure that an underlying algorithm localizes and recovers affected regions resulting in increased perceptual quality of a recovered image. To assess performance improvement, we perform extensive experiments alongside different region modification-based augmentation techniques and report observations such as improved performance, reduced requirement for training dataset, and early convergence across tasks such as low light image enhancement, image dehazing and image deblurring without any modification to baseline algorithm.