Related papers: SAPNet: Segmentation-Aware Progressive Network for…
In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions. In this paper, we propose an effective algorithm, called…
As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necessity for dense annotations by employing weakly-supervised…
Sea-land segmentation is an important process for many key applications in remote sensing. Proper operative sea-land segmentation for remote sensing images remains a challenging issue due to complex and diverse transition between sea and…
Complex scenario of ultrasound image, in which adjacent tissues (i.e., background) share similar intensity with and even contain richer texture patterns than lesion region (i.e., foreground), brings a unique challenge for accurate lesion…
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…
Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in the sense that they can be trained only on fully labeled…
With the increase in the number of image data and the lack of corresponding labels, weakly supervised learning has drawn a lot of attention recently in computer vision tasks, especially in the fine-grained semantic segmentation problem. To…
In recent years, artificial neural networks have achieved tremendous success for many vision-based tasks. However, this success remains within the paradigm of \emph{weak AI} where networks, among others, are specialized for just one given…
Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images. However, hyperspectral super-resolution remains…
With the rapid evolution of autonomous driving technology and intelligent transportation systems, semantic segmentation has become increasingly critical. Precise interpretation and analysis of real-world environments are indispensable for…
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem. We argue that by effectively aggregating features, a relatively simple network can still handle tough image…
Co-occurrent visual patterns suggest that pixel relation modeling facilitates dense prediction tasks, which inspires the development of numerous context modeling paradigms, \emph{e.g.}, multi-scale-driven and similarity-driven context…
The goal of salient region detection is to identify the regions of an image that attract the most attention. Many methods have achieved state-of-the-art performance levels on this task. Recently, salient instance segmentation has become an…
Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes…
We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling. SegNet has several attractive properties; (i) it only requires forward evaluation of a fully learnt function to obtain smooth label predictions, (ii)…
Side-scan sonar (SSS) imagery is widely used for seafloor mapping and underwater remote sensing, yet the measured intensity is strongly influenced by seabed reflectivity, terrain elevation, and acoustic path loss. This entanglement makes…
As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…
Underwater degraded images greatly challenge existing algorithms to detect objects of interest. Recently, researchers attempt to adopt attention mechanisms or composite connections for improving the feature representation of detectors.…
Inland water body segmentation from Synthetic Aperture Radar (SAR) images is an important task needed for several applications, such as flood mapping. While SAR sensors capture data in all-weather conditions as high-resolution images,…
Deep learning techniques have achieved great success in remote sensing image change detection. Most of them are supervised techniques, which usually require large amounts of training data and are limited to a particular application.…