Related papers: A Miniaturized Semantic Segmentation Method for Re…

We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learning is proposed to improve the accuracy of the neural…

U-net is an image segmentation technique developed primarily for medical image analysis that can precisely segment images using a scarce amount of training data. These traits provide U-net with a very high utility within the medical imaging…

High-resolution remote sensing images (HRRSIs) contain substantial ground object information, such as texture, shape, and spatial location. Semantic segmentation, which is an important task for element extraction, has been widely used in…

In recent years, layered image compression is demonstrated to be a promising direction, which encodes a compact representation of the input image and apply an up-sampling network to reconstruct the image. To further improve the quality of…

The paper introduces the weighted convolution, a novel approach to the convolution for signals defined on regular grids (e.g., 2D images) through the application of an optimal density function to scale the contribution of neighbouring…

In this work we consider the application of convolutional neural networks (CNNs) for pixel-wise labeling (a.k.a., semantic segmentation) of remote sensing imagery (e.g., aerial color or hyperspectral imagery). Remote sensing imagery is…

LiDAR-based semantic segmentation is critical in the fields of robotics and autonomous driving as it provides a comprehensive understanding of the scene. This paper proposes a lightweight and efficient projection-based semantic segmentation…

Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by…

Typical convolutional networks are trained and conducted on RGB images. However, images are often compressed for memory savings and efficient transmission in real-world applications. In this paper, we explore methods for performing semantic…

Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces…

As a common method in the field of computer vision, spatial attention mechanism has been widely used in semantic segmentation of remote sensing images due to its outstanding long-range dependency modeling capability. However, remote sensing…

Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operations in the CNN backbone. Most previous methods employ…

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs…

Labeling errors in remote sensing (RS) image segmentation datasets often remain implicit and subtle due to ambiguous class boundaries, mixed pixels, shadows, complex terrain features, and subjective annotator bias. Furthermore, the scarcity…

Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack…

The interest of compressive sampling in ultrasound imaging has been recently extensively evaluated by several research teams. Following the different application setups, it has been shown that the RF data may be reconstructed from a small…

Convolutional neural networks are modern models that are very efficient in many classification tasks. They were originally created for image processing purposes. Then some trials were performed to use them in different domains like natural…

Decoding remote sensing images to achieve high perceptual quality, particularly at low bitrates, remains a significant challenge. To address this problem, we propose the invertible neural network-based remote sensing image compression…

In this paper, we propose a compact network called CUNet (compact unsupervised network) to counter the image classification challenge. Different from the traditional convolutional neural networks learning filters by the time-consuming…

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…