Related papers: Zoomless Maps: External Labeling Methods for the I…

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…

Deep neural networks have reached high accuracy on object detection but their success hinges on large amounts of labeled data. To reduce the labels dependency, various active learning strategies have been proposed, typically based on the…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Modern self-driving autonomy systems heavily rely on deep learning. As a consequence, their performance is influenced significantly by the quality and richness of the training data. Data collecting platforms can generate many hours of raw…

We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model…

For autonomous vehicles to operate persistently in a typical urban environment, it is essential to have high accuracy position information. This requires a mapping and localisation system that can adapt to changes over time. A localisation…

High-definition (HD) maps are essential for autonomous driving, providing precise information such as road boundaries, lane dividers, and crosswalks to enable safe and accurate navigation. However, traditional HD map generation is…

Multi-label learning is concerned with the classification of data with multiple class labels. This is in contrast to the traditional classification problem where every data instance has a single label. Due to the exponential size of output…

We present a novel method for visual mapping and localization for autonomous vehicles, by extracting, modeling, and optimizing semantic road elements. Specifically, our method integrates cascaded deep models to detect standardized road…

Semantic map models visualize systematic relations among semantic functions through graph structures and are widely used in linguistic typology. However, existing construction methods either depend on labor-intensive expert reasoning or on…

In this paper, we address the problem of autonomous multi-robot mapping, exploration and navigation in unknown, GPS-denied indoor or urban environments using a swarm of robots equipped with directional sensors with limited sensing…

This paper introduces a real-time algorithm for navigating complex unknown environments cluttered with movable obstacles. Our algorithm achieves fast, adaptable routing by actively attempting to manipulate obstacles during path planning and…

We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data to label, and see…

For connected vehicles to have a substantial effect on road safety, it is required that accurate positions and trajectories can be shared. To this end, all vehicles must be accurately geolocalized in a common frame. This can be achieved by…

In reality, learning from multi-view multi-label data inevitably confronts three challenges: missing labels, incomplete views, and non-aligned views. Existing methods mainly concern the first two and commonly need multiple assumptions to…

Multi-label zero-shot learning (ZSL) is a more realistic counter-part of standard single-label ZSL since several objects can co-exist in a natural image. However, the occurrence of multiple objects complicates the reasoning and requires…

We present a solution to multi-robot distributed semantic mapping of novel and unfamiliar environments. Most state-of-the-art semantic mapping systems are based on supervised learning algorithms that cannot classify novel observations…

The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level…

Feature maps, that preserve the global topology of arbitrary datasets, can be formed by self-organizing competing agents. So far, it has been presumed that global interaction of agents is necessary for this process. We establish that this…

In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures…