As the data demand for deep learning models increases, active learning (AL) becomes essential to strategically select samples for labeling, which maximizes data efficiency and reduces training costs. Real-world scenarios necessitate the consideration of incomplete data knowledge within AL. Prior works address handling out-of-distribution (OOD) data, while another research direction has focused on category discovery. However, a combined analysis of real-world considerations combining AL with OOD data and category discovery remains unexplored. To address this gap, we propose Joint Out-of-distribution filtering and data Discovery Active learning (Joda)1, to uniquely address both challenges simultaneously by filtering out OOD data before selecting candidates for labeling. In contrast to previous methods, we deeply entangle the training procedure with filter and selection to construct a common feature space that aligns known and novel categories while separating OOD samples. Unlike previous works, Joda is highly efficient and completely omits auxiliary models and training access to the unlabeled pool for filtering or selection. In extensive experiments on 18 configurations and 3 metrics, Joda consistently achieves the highest accuracy with the best class discovery to OOD filtering balance compared to state-of-the-art competitor approaches.

In panoptic segmentation, individual instances must be separated within semantic classes. As state-of-the-art methods rely on a pre-defined set of classes, they struggle with novel categories and out-of-distribution (OOD) data. This is particularly problematic in safety-critical applications, such as autonomous driving, where reliability in unseen scenarios is essential. We address the gap between outstanding benchmark performance and reliability by proposing Prior2Former (P2F), the first approach for segmentation vision transformers rooted in evidential learning. P2F extends the mask vision transformer architecture by incorporating a Beta prior for computing model uncertainty in pixel-wise binary mask assignments. This design enables high-quality uncertainty estimation that effectively detects novel and OOD objects enabling state-of-the-art anomaly instance segmentation and open-world panoptic segmentation. Unlike most segmentation models addressing unknown classes, P2F operates without access to OOD data samples or contrastive training on void (i.e., unlabeled) classes, making it highly applicable in real-world scenarios where such prior information is unavailable. Additionally, P2F can be flexibly applied to anomaly instance and panoptic segmentation. Through comprehensive experiments on the Cityscapes, COCO, SegmentMeIfYouCan, and OoDIS datasets, P2F demonstrates state-of-the-art performance across the board.

In mobile robotics, particularly in autonomous driving, localization is one of the key challenges for navigation and planning. For safe operation in the open world where vulnerable participants are present, precise and guaranteed safe localization is required. While current classical fusion approaches are safe due to provably bounded closed-form formulation, their situation-adaptivity is limited. In contrast, data-driven approaches are situation-adaptive based on the underlying training data but unbounded and unsafe. In our work, we propose a novel data-driven but provably bounded sensor fusion and apply it to mobile robotic localization. In extensive experiments using an autonomous driving test vehicle, we show that our fusion method outperforms other safe fusion approaches.

Future self-driving cars must be able to perceive and understand their surroundings. Deep learning based approaches promise to solve the perception problem but require a large amount of manually labeled training data. Active learning is a training procedure in which the model itself selects interesting samples for labeling based on their uncertainty, with substantially less data required for training. Recent research in active learning has mostly focused on the simple image classification task. In this paper, we propose novel methods to estimate sample uncertainties for 2D and 3D object detection using Ensembles. We moreover evaluate different training strategies including Continuous Training to alleviate increasing training times introduced by the active learning cycle. Finally, we investigate the effects of active learning on imbalanced datasets and possible interactions with class weighting. Experiment results show both increased time saving around 55% and data saving rates of around 30%. For the 3D object detection task, we show that our proposed uncertainty estimation method is valid, saving 35% of labeling efforts and thus is ready for application for automotive object detection use cases.