Related papers: Reliability in Semantic Segmentation: Can We Use S…

Classical close-set semantic segmentation networks have limited ability to detect out-of-distribution (OOD) objects, which is important for safety-critical applications such as autonomous driving. Incrementally learning these OOD objects…

Modern machine learning models for scene understanding, such as depth estimation and object tracking, rely on large, high-quality datasets that mimic real-world deployment scenarios. To address data scarcity, we propose an end-to-end system…

A crucial requirement for reliable deployment of deep learning models for safety-critical applications is the ability to identify out-of-distribution (OOD) data points, samples which differ from the training data and on which a model might…

In this paper, we present a novel neural network using multi scale feature fusion at various scales for accurate and efficient semantic image segmentation. We used ResNet based feature extractor, dilated convolutional layers in downsampling…

Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and…

Recent advances in generative artificial intelligence have enabled the creation of high-quality synthetic data that closely mimics real-world data. This paper explores the adaptation of the Stable Diffusion 2.0 model for generating…

Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised…

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on inputs outside its training domain. For such out-of-distribution (OOD) inputs, the model can…

Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers…

We aim to solve semantic video segmentation in autonomous driving, namely road detection in real time video, using techniques discussed in (Shelhamer et al., 2016a). While fully convolutional network gives good result, we show that the…

Semantic segmentation has become an important task in computer vision with the growth of self-driving cars, medical image segmentation, etc. Although current models provide excellent results, they are still far from perfect and while there…

Over the past few years there has been major progress in the field of synthetic data generation using simulation based techniques. These methods use high-end graphics engines and physics-based ray-tracing rendering in order to represent the…

Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning perception algorithms trained solely on synthetic data encounter serious performance drops when they are…

Attacks on sensing and perception threaten the safe deployment of autonomous vehicles (AVs). Security-aware sensor fusion helps mitigate threats but requires accurate field of view (FOV) estimation which has not been evaluated autonomy. To…

The ability to detect failures and anomalies are fundamental requirements for building reliable systems for computer vision applications, especially safety-critical applications of semantic segmentation, such as autonomous driving and…

In this paper, we present a novel approach that combines deep metric learning and synthetic data generation using diffusion models for out-of-distribution (OOD) detection. One popular approach for OOD detection is outlier exposure, where…

Strategies that include the generation of synthetic data are beginning to be viable as obtaining real data can be logistically complicated, very expensive or slow. Not only the capture of the data can lead to complications, but also its…

The state of the art in human-centric computer vision achieves high accuracy and robustness across a diverse range of tasks. The most effective models in this domain have billions of parameters, thus requiring extremely large datasets,…

Advanced driving functions, for assistance or full automation, require strong guarantees to be deployed. This means that such functions may not be available all the time, like now commercially available SAE Level 3 modes that are made…