DeepAI AI Chat
Log In Sign Up

Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks

03/10/2021
by   Pranjay Shyam, et al.
0

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.

READ FULL TEXT

page 2

page 3

04/01/2020

Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy

Data augmentation is an effective way to improve the performance of deep...
01/13/2020

GridMask Data Augmentation

We propose a novel data augmentation method `GridMask' in this paper. It...
03/20/2022

Transparency strategy-based data augmentation for BI-RADS classification of mammograms

Image augmentation techniques have been widely investigated to improve t...
05/14/2023

SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistency

Images captured under low-light conditions are often plagued by several ...
11/22/2022

Rethinking Implicit Neural Representations for Vision Learners

Implicit Neural Representations (INRs) are powerful to parameterize cont...
11/02/2019

Segment for Restoration, Restore for Segmentation

Most state-of-the-art semantic segmentation or scene parsing approaches ...
08/19/2022

Low-light Enhancement Method Based on Attention Map Net

Low-light image enhancement is a crucial preprocessing task for some com...