Related papers: Wavelet-based Bi-dimensional Aggregation Network f…
Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation.…
Change detection is one of the fundamental applications of synthetic aperture radar (SAR) images. However, speckle noise presented in SAR images has a much negative effect on change detection. In this research, a novel two-phase…
Tiny object detection has gained considerable attention in the research community owing to the frequent occurrence of tiny objects in numerous critical real-world scenarios. However, convolutional neural networks (CNNs) used as the backbone…
Synthetic Aperture Radar (SAR) images have proven to be a valuable cue for multimodal Land Cover Classification (LCC) when combined with RGB images. Most existing studies on cross-modal fusion assume that consistent feature information is…
Facial expression manipulation aims to change human facial expressions without affecting face recognition. In order to transform the facial expressions to target expressions, previous methods relied on expression labels to guide the…
As wireless communication systems evolve, automatic modulation recognition (AMR) plays a key role in improving spectrum efficiency, especially in cognitive radio systems. Traditional AMR methods face challenges in complex, noisy…
Recent salient object detection (SOD) models predominantly rely on heavyweight backbones, incurring substantial computational cost and hindering their practical application in various real-world settings, particularly on edge devices. This…
To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality…
Airborne Laser Scanning (ALS) point clouds have complex structures, and their 3D semantic labeling has been a challenging task. It has three problems: (1) the difficulty of classifying point clouds around boundaries of objects from…
Multi-organ segmentation in medical image analysis is crucial for diagnosis and treatment planning. However, many factors complicate the task, including variability in different target categories and interference from complex backgrounds.…
Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote…
Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…
The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has…
A new fangled method for ship wake detection in synthetic aperture radar (SAR) images is explored here. Most of the detection procedure applies the Radon transform as its properties outfit more than any other transformation for the…
The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create challenges. We propose CAE-Net, a Convolution- and…
Hazy images are often subject to color distortion, blurring, and other visible quality degradation. Some existing CNN-based methods have great performance on removing homogeneous haze, but they are not robust in non-homogeneous case. The…
Natural image quality is often degraded by adverse weather conditions, significantly impairing the performance of downstream tasks. Image restoration has emerged as a core solution to this challenge and has been widely discussed in the…
The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNNs). However, the weights sampling strategy of WSNet…
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…
Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing…