Related papers: AuxNet: Auxiliary tasks enhanced Semantic Segmenta…

Road scene understanding tasks have recently become crucial for self-driving vehicles. In particular, real-time semantic segmentation is indispensable for intelligent self-driving agents to recognize roadside objects in the driving area. As…

This paper presents the preliminary findings of a semi-supervised segmentation method for extracting roads from sattelite images. Artificial Neural Networks and image segmentation methods are among the most successful methods for extracting…

In fine-grained road scene understanding, semantic segmentation plays a crucial role in enabling vehicles to perceive and comprehend their surroundings. By assigning a specific class label to each pixel in an image, it allows for precise…

Two factors have proven to be very important to the performance of semantic segmentation models: global context and multi-level semantics. However, generating features that capture both factors always leads to high computational complexity,…

Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively…

Scene segmentation is widely used in the field of autonomous driving for environment perception, and semantic scene segmentation (3S) has received a great deal of attention due to the richness of the semantic information it contains. It…

While deep learning has been very beneficial in data-rich settings, tasks with smaller training set often resort to pre-training or multitask learning to leverage data from other tasks. In this case, careful consideration is needed to…

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…

Spannotation is an open source user-friendly tool developed for image annotation for semantic segmentation specifically in autonomous navigation tasks. This study provides an evaluation of Spannotation, demonstrating its effectiveness in…

Instance segmentation is crucial for autonomous driving, but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring knowledge from labeled…

Machine learning has been utilized to perform tasks in many different domains such as classification, object detection, image segmentation and natural language analysis. Data labeling has always been one of the most important tasks in…

Deep neural network models for image segmentation can be a powerful tool for the automation of motor claims handling processes in the insurance industry. A crucial aspect is the reliability of the model outputs when facing adverse…

This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city.…

This work tackles scene understanding for outdoor robotic navigation, solely relying on images captured by an on-board camera. Conventional visual scene understanding interprets the environment based on specific descriptive categories.…

Shape and pose estimation is a critical perception problem for a self-driving car to fully understand its surrounding environment. One fundamental challenge in solving this problem is the incomplete sensor signal (e.g., LiDAR scans),…

3D occupancy prediction provides dense spatial understanding critical for safe autonomous driving. However, this task suffers from a severe class imbalance due to its volumetric representation, where safety-critical objects (bicycles,…

Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality,…

Autonomous driving techniques have been flourishing in recent years while thirsting for huge amounts of high-quality data. However, it is difficult for real-world datasets to keep up with the pace of changing requirements due to their…

Manual visual inspection performed by certified inspectors is still the main form of road pothole detection. This process is, however, not only tedious, time-consuming and costly, but also dangerous for the inspectors. Furthermore, the road…

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…