Related papers: Rethinking Skip Connections in Encoder-decoder Net…

Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decoder-based architectures have been found to be useful due to…

In this paper, we study the influence of both long and short skip connections on Fully Convolutional Networks (FCN) for biomedical image segmentation. In standard FCNs, only long skip connections are used to skip features from the…

The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder…

Skip connection engineering is primarily employed to address the semantic gap between the encoder and decoder, while also integrating global dependencies to understand the relationships among complex anatomical structures in medical image…

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients. They equip encoder-decoder-like…

Although convolutional neural networks (CNNs) are promoting the development of medical image semantic segmentation, the standard model still has some shortcomings. First, the feature mapping from the encoder and decoder sub-networks in the…

Encoder-decoder architectures are widely adopted for medical image segmentation tasks. With the lateral skip connection, the models can obtain and fuse both semantic and resolution information in deep layers to achieve more accurate…

Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection. Recently, learning-based algorithms achieve huge success in depth estimation by…

Single encoder-decoder methodologies for semantic segmentation are reaching their peak in terms of segmentation quality and efficiency per number of layers. To address these limitations, we propose a new architecture based on a decoder…

In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and de-convolution operators,…

Since the study of deep convolutional neural network became prevalent, one of the important discoveries is that a feature map from a convolutional network can be extracted before going into the fully connected layer and can be used as a…

The prevalence of skin melanoma is rapidly increasing as well as the recorded death cases of its patients. Automatic image segmentation tools play an important role in providing standardized computer-assisted analysis for skin melanoma…

Depth estimation from monocular images is a challenging problem in computer vision. In this paper, we tackle this problem using a novel network architecture using multi scale feature fusion. Our network uses two different blocks, first…

Depth information is the foundation of perception, essential for autonomous driving, robotics, and other source-constrained applications. Promptly obtaining accurate and efficient depth information allows for a rapid response in dynamic…

We present an approach for estimating surface normals from in-the-wild color images of faces. While data-driven strategies have been proposed for single face images, limited available ground truth data makes this problem difficult. To…

Recent deep CNNs contain forward shortcut connections; i.e. skip connections from low to high layers. Reusing features from lower layers that have higher resolution (location information) benefit higher layers to recover lost details and…

Monocular depth estimation is an ambiguous problem, thus global structural cues play an important role in current data-driven single-view depth estimation methods. Panorama images capture the complete spatial information of their…

In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution. Compared with two representative network architectures with skip…

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring…

In this paper, we introduce RED-NET: A Recursive Encoder-Decoder Network with Skip-Connections for edge detection in natural images. The proposed network is a novel integration of a Recursive Neural Network with an Encoder-Decoder…