Alexander Braun

Johannes Haug, Alexander Braun, Stefan Zürn et al.

As complex machine learning models are increasingly used in sensitive applications like banking, trading or credit scoring, there is a growing demand for reliable explanation mechanisms. Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. However, attribution methods typically assume a stationary environment in which the predictive model has been trained and remains stable. As a result, it is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. In this paper, we discuss the impact of temporal change on local feature attributions. In particular, we show that local attributions can become obsolete each time the predictive model is updated or concept drift alters the data generating distribution. Consequently, local feature attributions in data streams provide high explanatory power only when combined with a mechanism that allows us to detect and respond to local changes over time. To this end, we present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift. CDLEEDS serves as an intuitive extension of attribution-based explanation techniques to identify outdated local attributions and enable more targeted recalculations. In experiments, we also show that the proposed framework can reliably detect both local and global concept drift. Accordingly, our work contributes to a more meaningful and robust explainability in online machine learning.

Christopher Lang, Alexander Braun, Lars Schillingmann et al.

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification tasks, the potential to learn dense representations from sequential data has been relatively unexplored. In this work, we propose TempO, a temporal ordering pretext task for pre-training region-level feature representations for perception tasks. We embed each frame by an unordered set of proposal feature vectors, a representation that is natural for object detection or tracking systems, and formulate the sequential ordering by predicting frame transition probabilities in a transformer-based multi-frame architecture whose complexity scales less than quadratic with respect to the sequence length. Extensive evaluations on the BDD100K, nuImages, and MOT17 datasets show that our TempO pre-training approach outperforms single-frame self-supervised learning methods as well as supervised transfer learning initialization strategies, achieving an improvement of +0.7% in mAP for object detection and +2.0% in the HOTA score for multi-object tracking.

Christopher Lang, Alexander Braun, Lars Schillingmann et al.

Self-supervised multi-object trackers have tremendous potential as they enable learning from raw domain-specific data. However, their re-identification accuracy still falls short compared to their supervised counterparts. We hypothesize that this drawback results from formulating self-supervised objectives that are limited to single frames or frame pairs. Such formulations do not capture sufficient visual appearance variations to facilitate learning consistent re-identification features for autonomous driving when the frame rate is low or object dynamics are high. In this work, we propose a training objective that enables self-supervised learning of re-identification features from multiple sequential frames by enforcing consistent association scores across short and long timescales. We perform extensive evaluations demonstrating that re-identification features trained from longer sequences significantly reduce ID switches on standard autonomous driving datasets compared to existing self-supervised learning methods, which are limited to training on frame pairs. Using our proposed SubCo loss function, we set the new state-of-the-art among self-supervised methods and even perform on par with fully supervised learning methods.

Christopher Lang, Alexander Braun, Abhinav Valada

Object detection, for the most part, has been formulated in the euclidean space, where euclidean or spherical geodesic distances measure the similarity of an image region to an object class prototype. In this work, we study whether a hyperbolic geometry better matches the underlying structure of the object classification space. We incorporate a hyperbolic classifier in two-stage, keypoint-based, and transformer-based object detection architectures and evaluate them on large-scale, long-tailed, and zero-shot object detection benchmarks. In our extensive experimental evaluations, we observe categorical class hierarchies emerging in the structure of the classification space, resulting in lower classification errors and boosting the overall object detection performance.

Christopher Lang, Alexander Braun, Lars Schillingmann et al.

Multi-task networks can potentially improve performance and computational efficiency compared to single-task networks, facilitating online deployment. However, current multi-task architectures in point cloud perception combine multiple task-specific point cloud representations, each requiring a separate feature encoder and making the network structures bulky and slow. We propose PAttFormer, an efficient multi-task architecture for joint semantic segmentation and object detection in point clouds that only relies on a point-based representation. The network builds on transformer-based feature encoders using neighborhood attention and grid-pooling and a query-based detection decoder using a novel 3D deformable-attention detection head design. Unlike other LiDAR-based multi-task architectures, our proposed PAttFormer does not require separate feature encoders for multiple task-specific point cloud representations, resulting in a network that is 3x smaller and 1.4x faster while achieving competitive performance on the nuScenes and KITTI benchmarks for autonomous driving perception. Our extensive evaluations show substantial gains from multi-task learning, improving LiDAR semantic segmentation by +1.7% in mIou and 3D object detection by +1.7% in mAP on the nuScenes benchmark compared to the single-task models.

Christopher Lang, Alexander Braun, Abhinav Valada

Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a background class, disregarding any similarities in the object types. In this work, we compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs that are widely applied in open world object detection. Extensive experimental results on multiple knowledge-embeddings as well as distance metrics indicate that knowledge-based class representations result in more semantically grounded misclassifications while performing on par compared to one-hot methods on the challenging COCO and Cityscapes object detection benchmarks. We generalize our findings to multiple object detection architectures by proposing a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.

George Eskandar, Alexander Braun, Martin Meinke et al.

Predicting future 3D LiDAR pointclouds is a challenging task that is useful in many applications in autonomous driving such as trajectory prediction, pose forecasting and decision making. In this work, we propose a new LiDAR prediction framework that is based on generative models namely Variational Recurrent Neural Networks (VRNNs), titled Stochastic LiDAR Prediction and Completion (SLPC). Our algorithm is able to address the limitations of previous video prediction frameworks when dealing with sparse data by spatially inpainting the depth maps in the upcoming frames. Our contributions can thus be summarized as follows: we introduce the new task of predicting and completing depth maps from spatially sparse data, we present a sparse version of VRNNs and an effective self-supervised training method that does not require any labels. Experimental results illustrate the effectiveness of our framework in comparison to the state of the art methods in video prediction.