Related papers: Lookahead Adversarial Learning for Near Real-Time …

We introduce a new method for generating color images from sketches or edge maps. Current methods either require some form of additional user-guidance or are limited to the "paired" translation approach. We argue that segmentation…

This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an…

Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…

This work provides a framework for addressing the problem of supervised domain adaptation with deep models. The main idea is to exploit adversarial learning to learn an embedded subspace that simultaneously maximizes the confusion between…

The success of state-of-the-art deep neural networks heavily relies on the presence of large-scale labelled datasets, which are extremely expensive and time-consuming to annotate. This paper focuses on tackling semi-supervised part…

With the introduction of fully convolutional neural networks, deep learning has raised the benchmark for medical image segmentation on both speed and accuracy, and different networks have been proposed for 2D and 3D segmentation with…

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…

Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most…

LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public…

Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…

To improve logical anomaly detection, some previous works have integrated segmentation techniques with conventional anomaly detection methods. Although these methods are effective, they frequently lead to unsatisfactory segmentation results…

One of the fundamental challenges in the design of perception systems for autonomous vehicles is validating the performance of each algorithm under a comprehensive variety of operating conditions. In the case of vision-based semantic…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…

Stable feature extraction is the key for the Loop closure detection (LCD) task in the simultaneously localization and mapping (SLAM) framework. In our paper, the feature extraction is operated by using a generative adversarial networks…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

Semantic segmentation requires pixel-level annotation, which is time-consuming. Active Learning (AL) is a promising method for reducing data annotation costs. Due to the gap between aerial and natural images, the previous AL methods are not…

Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task. The effect of this type of training on semantic segmentation, contrarily, just…

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…

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality of synthesized images is far from satisfactory due to three…