Related papers: Traffic Scene Similarity: a Graph-based Contrastiv…

Handling large amounts of data has become a key for developing automated driving systems. Especially for developing highly automated driving functions, working with images has become increasingly challenging due to the sheer size of the…

This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction. Given the scarcity and strong imbalance of data samples, we propose a…

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

Graph anomaly detection is a popular and vital task in various real-world scenarios, which has been studied for several decades. Recently, many studies extending deep learning-based methods have shown preferable performance on graph anomaly…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

A modification of the Random Forest algorithm for the categorization of traffic situations is introduced in this paper. The procedure yields an unsupervised machine learning method. The algorithm generates a proximity matrix which contains…

Contrastive pretraining techniques for text classification has been largely studied in an unsupervised setting. However, oftentimes labeled data from related tasks which share label semantics with current task is available. We hypothesize…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting…

Discriminating the traversability of terrains is a crucial task for autonomous driving in off-road environments. However, it is challenging due to the diverse, ambiguous, and platform-specific nature of off-road traversability. In this…

Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images. Most existing methods address this…

Graph contrastive learning (GCL) aligns node representations by classifying node pairs into positives and negatives using a selection process that typically relies on establishing correspondences within two augmented graphs. The…

Detecting tampered text in document images is a challenging task due to data scarcity. To address this, previous work has attempted to generate tampered documents using rule-based methods. However, the resulting documents often suffer from…

This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying the graph categories in scenarios with imbalanced class distributions. While graph neural networks (GNNs) have achieved…

Unsupervised graph representation learning has emerged as a powerful tool to address real-world problems and achieves huge success in the graph learning domain. Graph contrastive learning is one of the unsupervised graph representation…

Clustering traffic scenarios and detecting novel scenario types are required for scenario-based testing of autonomous vehicles. These tasks benefit from either good similarity measures or good representations for the traffic scenarios. In…

Learning-based methods have become increasingly popular for solving vehicle routing problems due to their near-optimal performance and fast inference speed. Among them, the combination of deep reinforcement learning and graph representation…

As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a…

Most scene graph parsers use a two-stage pipeline to detect visual relationships: the first stage detects entities, and the second predicts the predicate for each entity pair using a softmax distribution. We find that such pipelines,…

Graph representation learning has long been an important yet challenging task for various real-world applications. However, their downstream tasks are mainly performed in the settings of supervised or semi-supervised learning. Inspired by…