Related papers: Promoting Connectivity of Network-Like Structures …

Vehicle re-identification is an important computer vision task where the objective is to identify a specific vehicle among a set of vehicles seen at various viewpoints. Recent methods based on deep learning utilize a global average pooling…

Automatic Extraction of road network from satellite images is a goal that can benefit and even enable new technologies. Methods that combine machine learning (ML) and computer vision have been proposed in recent years which make the task…

Creating high definition maps that contain precise information of static elements of the scene is of utmost importance for enabling self driving cars to drive safely. In this paper, we tackle the problem of drivable road boundary extraction…

A successful deep learning network is highly dependent not only on the training dataset, but the training algorithm used to condition the network for a given task. The loss function, dataset, and tuning of hyperparameters all play an…

Segmentation networks are not explicitly imposed to learn global invariants of an image, such as the shape of an object and the geometry between multiple objects, when they are trained with a standard loss function. On the other hand,…

Semantic instance segmentation remains a challenging task. In this work we propose to tackle the problem with a discriminative loss function, operating at the pixel level, that encourages a convolutional network to produce a representation…

Neural network training is commonly based on SGD. However, the understanding of SGD's ability to converge to good local minima, given the non-convex nature of loss functions and the intricate geometric characteristics of loss landscapes,…

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…

Network tomography aims at inferring internal network characteristics based on measurements at the edge of the network. In loss tomography, in particular, the characteristic of interest is the loss rate of individual links and multicast…

The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function. The majority of objective functions for neural models can be divided into metric learning and…

Simultaneous segmentation of multiple organs from different medical imaging modalities is a crucial task as it can be utilized for computer-aided diagnosis, computer-assisted surgery, and therapy planning. Thanks to the recent advances in…

Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust…

Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network…

Road extraction in remote sensing images is of great importance for a wide range of applications. Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears…

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…

Recently, deep neural networks have achieved impressive performance in terms of both reconstruction accuracy and efficiency for single image super-resolution (SISR). However, the network model of these methods is a fully convolutional…

We propose Region-wise (RW) loss for biomedical image segmentation. Region-wise loss is versatile, can simultaneously account for class imbalance and pixel importance, and it can be easily implemented as the pixel-wise multiplication…

Besides per-pixel accuracy, topological correctness is also crucial for the segmentation of images with fine-scale structures, e.g., satellite images and biomedical images. In this paper, by leveraging the theory of digital topology, we…

Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels…

Low-dose CT denoising is a challenging task that has been studied by many researchers. Some studies have used deep neural networks to improve the quality of low-dose CT images and achieved fruitful results. In this paper, we propose a deep…