Related papers: DAMix: A Density-Aware Mixup Augmentation for Sing…

We propose an enhanced multi-scale network, dubbed GridDehazeNet+, for single image dehazing. The proposed dehazing method does not rely on the Atmosphere Scattering Model (ASM), and an explanation as to why it is not necessarily performing…

Demosaicking and denoising are among the most crucial steps of modern digital camera pipelines and their joint treatment is a highly ill-posed inverse problem where at-least two-thirds of the information are missing and the rest are…

Deep learning-based source dehazing methods trained on synthetic datasets have achieved remarkable performance but suffer from dramatic performance degradation on real hazy images due to domain shift. Although certain Domain Adaptation (DA)…

Deep neural networks have emerged as very successful tools for image restoration and reconstruction tasks. These networks are often trained end-to-end to directly reconstruct an image from a noisy or corrupted measurement of that image. To…

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to…

Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a…

While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial…

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…

Image alignment by mesh warps, such as meshflow, is a fundamental task which has been widely applied in various vision applications(e.g., multi-frame HDR/denoising, video stabilization). Traditional mesh warp methods detect and match image…

Deep neural networks (DNNs) have shown exciting performance in various tasks, yet suffer generalization failures when meeting unknown target domains. One of the most promising approaches to achieve domain generalization (DG) is generating…

Generalizable person re-identification (Re-ID) aims to recognize individuals across unseen cameras and environments. While existing methods rely heavily on limited labeled multi-camera data, we propose DynaMix, a novel method that…

Indoor localization is a challenging problem that - unlike outdoor localization - lacks a universal and robust solution. Machine Learning (ML), particularly Deep Learning (DL), methods have been investigated as a promising approach.…

Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of…

Deep Metric Learning (DML) serves to learn an embedding function to project semantically similar data into nearby embedding space and plays a vital role in many applications, such as image retrieval and face recognition. However, the…

Data Augmentation (DA) is a technique to increase the quantity and diversity of the training data, and by that alleviate overfitting and improve generalisation. However, standard DA produces synthetic data for augmentation with limited…

Single image dehazing is an ill-posed problem that has recently drawn important attention. Despite the significant increase in interest shown for dehazing over the past few years, the validation of the dehazing methods remains largely…

Removing the noise and improving the visual quality of hyperspectral images (HSIs) is challenging in academia and industry. Great efforts have been made to leverage local, global or spectral context information for HSI denoising. However,…

Image dehazing is one of the important and popular topics in computer vision and machine learning. A reliable real-time dehazing method with reliable performance is highly desired for many applications such as autonomous driving, security…

The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although the trained networks can improve the segmentation…

Image dehazing is quite challenging in dense-haze scenarios, where quite less original information remains in the hazy image. Though previous methods have made marvelous progress, they still suffer from information loss in content and color…