English
Related papers

Related papers: Data augmentation to improve robustness of image c…

200 papers

Resolution enhancements are often desired in imaging applications where high-resolution sensor arrays are difficult to obtain. Many computational imaging methods have been proposed to encode high-resolution scene information on…

Image and Video Processing · Electrical Eng. & Systems 2018-10-29 Kevin Beale , Jianbo Chen , Kevin F. Kelly , Justin Romberg

Moving objects are frequently seen in daily life and usually appear blurred in images due to their motion. While general object retrieval is a widely explored area in computer vision, it primarily focuses on sharp and static objects, and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Rong Zou , Marc Pollefeys , Denys Rozumnyi

Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Markus Heinonen , Ba-Hien Tran , Michael Kampffmeyer , Maurizio Filippone

This paper proposes a new technique based on a non-linear Minmax Detector Based (MDB) filter for image restoration. The aim of image enhancement is to reconstruct the true image from the corrupted image. The process of image acquisition…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 S. K. Satpathy , S. Panda , K. K. Nagwanshi , C. Ardil

This paper investigates the impact of various data augmentation techniques on the performance of object detection models. Specifically, we explore classical augmentation methods, image compositing, and advanced generative models such as…

Computer Vision and Pattern Recognition · Computer Science 2025-02-20 Ang Jia Ning Shermaine , Michalis Lazarou , Tania Stathaki

Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains…

Machine Learning · Computer Science 2019-06-07 Raphael Gontijo Lopes , Dong Yin , Ben Poole , Justin Gilmer , Ekin D. Cubuk

Robotics applications in urban environments are subject to obstacles that exhibit specular reflections hampering autonomous navigation. On the other hand, these reflections are highly polarized and this extra information can successfully be…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Marc Blanchon , Olivier Morel , Fabrice Meriaudeau , Ralph Seulin , Désiré Sidibé

Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Shentong Mo , Zhun Sun , Chao Li

In this work, we have presented a way to increase the contrast of an image. Our target is to find a transformation that will be image specific. We have used a fuzzy system as our transformation function. To tune the system according to an…

Computer Vision and Pattern Recognition · Computer Science 2023-01-31 Mohimenul Kabir , Jaiaid Mobin , Ahmad Hassanat , M. Sohel Rahman

One of the main limitations for the resolution of optical instruments is the size of the sensor's pixels. In this paper we introduce a new sub pixel resolution algorithm to enhance the resolution of images. This method is based on the…

Instrumentation and Detectors · Physics 2012-11-12 Siamak Khademi , Ahmad Darudi , Zahra Abbasi

Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has…

Machine Learning · Computer Science 2020-01-09 Sungbin Lim , Ildoo Kim , Taesup Kim , Chiheon Kim , Sungwoong Kim

Recent advancements in lidar technology have led to improved point cloud resolution as well as the generation of 360 degrees, low-resolution images by encoding depth, reflectivity, or near-infrared light within each pixel. These images…

Robotics · Computer Science 2025-05-06 Sier Ha , Honghao Du , Xianjia Yu , Tomi Westerlund

Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion and defocus.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Kaihao Zhang , Tao Wang , Wenhan Luo , Boheng Chen , Wenqi Ren , Bjorn Stenger , Wei Liu , Hongdong Li , Ming-Hsuan Yang

Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across…

Machine Learning · Computer Science 2020-09-18 Dong Yin , Raphael Gontijo Lopes , Jonathon Shlens , Ekin D. Cubuk , Justin Gilmer

Removing multiple degradations, such as haze, rain, and blur, from real-world images poses a challenging and illposed problem. Recently, unified models that can handle different degradations have been proposed and yield promising results.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Yongheng Zhang , Danfeng Yan , Yuanqiang Cai

Motion blur, caused by relative movement between camera and scene during exposure, significantly degrades image quality and impairs downstream computer vision tasks such as object detection, tracking, and recognition in dynamic…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Shamika Likhite , Santiago López-Tapia , Aggelos K. Katsaggelos

The usage of digital content (photos and videos) in a variety of applications has increased due to the popularity of multimedia devices. These uses include advertising campaigns, educational resources, and social networking platforms. There…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Muhammad Turab

A novel method to convert color/multi-spectral images to gray-level images is introduced to increase the performance of document binarization methods. The method uses the distribution of the pixel data of the input document image in a color…

Computer Vision and Pattern Recognition · Computer Science 2013-06-27 Reza Farrahi Moghaddam , Shaohua Chen , Rachid Hedjam , Mohamed Cheriet

Low-light images often suffer from noise and color distortion. Object detection, semantic segmentation, instance segmentation, and other tasks are challenging when working with low-light images because of image noise and chromatic…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Xiaochun Lei , Weiliang Mai , Junlin Xie , He Liu , Zetao Jiang , Zhaoting Gong , Chang Lu , Linjun Lu

Recently, the state-of-the-art models for image captioning have overtaken human performance based on the most popular metrics, such as BLEU, METEOR, ROUGE, and CIDEr. Does this mean we have solved the task of image captioning? The above…

Computer Vision and Pattern Recognition · Computer Science 2019-05-16 Qingzhong Wang , Antoni B. Chan