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

Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the…

Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are…

Images with haze of different varieties often pose a significant challenge to dehazing. Therefore, guidance by estimates of haze parameters related to the variety would be beneficial, and their progressive update jointly with haze reduction…

Multi-stage architectures have exhibited efficacy in image dehazing, which usually decomposes a challenging task into multiple more tractable sub-tasks and progressively estimates latent hazy-free images. Despite the remarkable progress,…

Given an existing trained neural network, it is often desirable to learn new capabilities without hindering performance of those already learned. Existing approaches either learn sub-optimal solutions, require joint training, or incur a…

The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models…

Advanced data augmentation strategies have widely been studied to improve the generalization ability of deep learning models. Regional dropout is one of the popular solutions that guides the model to focus on less discriminative parts by…

Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bottleneck in low label settings such as Semi-Supervised…

Domain gaps between training data (source) and real-world environments (target) often degrade the performance of object detection models. Most existing methods aim to bridge this gap by aligning features across source and target domains but…

Removing adverse weather conditions like rain, fog, and snow from images is a challenging problem. Although the current recovery algorithms targeting a specific condition have made impressive progress, it is not flexible enough to deal with…

Reducing the atmospheric haze and enhancing image clarity is crucial for computer vision applications. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often lack diverse haze types, impeding effective…

Image dehazing has witnessed significant advancements with the development of deep learning models. However, most existing methods focus solely on single-modal RGB features, neglecting the inherent correlation between scene depth and haze…

Optical remote sensing image dehazing presents significant challenges due to its extensive spatial scale and highly non-uniform haze distribution, which traditional single-image dehazing methods struggle to address effectively. While…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

Labeling semantic segmentation datasets is a costly and laborious process if compared with tasks like image classification and object detection. This is especially true for remote sensing applications that not only work with extremely high…

Image alignment across domains has recently become one of the realistic and popular topics in the research community. In this problem, a deep learning-based image alignment method is usually trained on an available largescale database.…

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…

Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing. Conventional methods rely on some heuristics to handcraft various priors to remove or separate the…

We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level…

Diffusion models have recently emerged as the dominant approach in visual generation tasks. However, the lengthy denoising chains and the computationally intensive noise estimation networks hinder their applicability in low-latency and…