Heiko Neumann

David B. Adrian, Andras Gabor Kupcsik, Markus Spies et al.

We propose a framework for robust and efficient training of Dense Object Nets (DON) with a focus on multi-object robot manipulation scenarios. DON is a popular approach to obtain dense, view-invariant object descriptors, which can be used for a multitude of downstream tasks in robot manipulation, such as, pose estimation, state representation for control, etc.. However, the original work focused training on singulated objects, with limited results on instance-specific, multi-object applications. Additionally, a complex data collection pipeline, including 3D reconstruction and mask annotation of each object, is required for training. In this paper, we further improve the efficacy of DON with a simplified data collection and training regime, that consistently yields higher precision and enables robust tracking of keypoints with less data requirements. In particular, we focus on training with multi-object data instead of singulated objects, combined with a well-chosen augmentation scheme. We additionally propose an alternative loss formulation to the original pixelwise formulation that offers better results and is less sensitive to hyperparameters. Finally, we demonstrate the robustness and accuracy of our proposed framework on a real-world robotic grasping task.

Felix Ott, Nisha Lakshmana Raichur, David Rügamer et al.

Visual-inertial localization is a key problem in computer vision and robotics applications such as virtual reality, self-driving cars, and aerial vehicles. The goal is to estimate an accurate pose of an object when either the environment or the dynamics are known. Absolute pose regression (APR) techniques directly regress the absolute pose from an image input in a known scene using convolutional and spatio-temporal networks. Odometry methods perform relative pose regression (RPR) that predicts the relative pose from a known object dynamic (visual or inertial inputs). The localization task can be improved by retrieving information from both data sources for a cross-modal setup, which is a challenging problem due to contradictory tasks. In this work, we conduct a benchmark to evaluate deep multimodal fusion based on pose graph optimization and attention networks. Auxiliary and Bayesian learning are utilized for the APR task. We show accuracy improvements for the APR-RPR task and for the RPR-RPR task for aerial vehicles and hand-held devices. We conduct experiments on the EuRoC MAV and PennCOSYVIO datasets and record and evaluate a novel industry dataset.

Johannes Flotzinger, Fabian Deuser, Achref Jaziri et al.

Adequate bridge inspection is increasingly challenging in many countries due to growing ailing stocks, compounded with a lack of staff and financial resources. Automating the key task of visual bridge inspection, classification of defects and building components on pixel level, improves efficiency, increases accuracy and enhances safety in the inspection process and resulting building assessment. Models overtaking this task must cope with an assortment of real-world conditions. They must be robust to variations in image quality, as well as background texture, as defects often appear on surfaces of diverse texture and degree of weathering. dacl10k is the largest and most diverse dataset for real-world concrete bridge inspections. However, the dataset exhibits class imbalance, which leads to notably poor model performance particularly when segmenting fine-grained classes such as cracks and cavities. This work introduces "synth-dacl", a compilation of three novel dataset extensions based on synthetic concrete textures. These extensions are designed to balance class distribution in dacl10k and enhance model performance, especially for crack and cavity segmentation. When incorporating the synth-dacl extensions, we observe substantial improvements in model robustness across 15 perturbed test sets. Notably, on the perturbed test set, a model trained on dacl10k combined with all synthetic extensions achieves a 2% increase in mean IoU, F1 score, Recall, and Precision compared to the same model trained solely on dacl10k.

David B. Adrian, Andras Gabor Kupcsik, Markus Spies et al.

Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be learned efficiently using self-supervision, and they can encode actuated and even non-rigid objects. However, learning robust, view-invariant keypoints in a self-supervised approach requires a meticulous data collection approach involving precise calibration and expert supervision. In this paper we introduce Cycle-Correspondence Loss (CCL) for view-invariant dense descriptor learning, which adopts the concept of cycle-consistency, enabling a simple data collection pipeline and training on unpaired RGB camera views. The key idea is to autonomously detect valid pixel correspondences by attempting to use a prediction over a new image to predict the original pixel in the original image, while scaling error terms based on the estimated confidence. Our evaluation shows that we outperform other self-supervised RGB-only methods, and approach performance of supervised methods, both with respect to keypoint tracking as well as for a robot grasping downstream task.

Michael Winter, Heiko Neumann, Rüdiger Pryss et al.

Process models depict crucial artifacts for organizations regarding documentation, communication, and collaboration. The proper comprehension of such models is essential for an effective application. An important aspect in process model literacy constitutes the question how the information presented in process models is extracted and processed by the human visual system? For such visuospatial tasks, the visual system deploys a set of elemental operations, from whose compositions different visual routines are produced. This paper provides insights from an exploratory eye tracking study, in which visual routines during process model comprehension were contemplated. More specifically, n = 29 participants were asked to comprehend n = 18 process models expressed in the Business Process Model and Notation 2.0 reflecting diverse mappings (i.e., straight, upward, downward) and complexity levels. The performance measures indicated that even less complex process models pose a challenge regarding their comprehension. The upward mapping confronted participants' attention with more challenges, whereas the downward mapping was comprehended more effectively. Based on recorded eye movements, three gaze patterns applied during model comprehension were derived. Thereupon, we defined a general model which identifies visual routines and corresponding elemental operations during process model comprehension. Finally, implications for practice as well as research and directions for future work are discussed in this paper.

Yan Zhang, Mohamed Hassan, Heiko Neumann et al.

We present a fully automatic system that takes a 3D scene and generates plausible 3D human bodies that are posed naturally in that 3D scene. Given a 3D scene without people, humans can easily imagine how people could interact with the scene and the objects in it. However, this is a challenging task for a computer as solving it requires that (1) the generated human bodies to be semantically plausible within the 3D environment (e.g. people sitting on the sofa or cooking near the stove), and (2) the generated human-scene interaction to be physically feasible such that the human body and scene do not interpenetrate while, at the same time, body-scene contact supports physical interactions. To that end, we make use of the surface-based 3D human model SMPL-X. We first train a conditional variational autoencoder to predict semantically plausible 3D human poses conditioned on latent scene representations, then we further refine the generated 3D bodies using scene constraints to enforce feasible physical interaction. We show that our approach is able to synthesize realistic and expressive 3D human bodies that naturally interact with 3D environment. We perform extensive experiments demonstrating that our generative framework compares favorably with existing methods, both qualitatively and quantitatively. We believe that our scene-conditioned 3D human generation pipeline will be useful for numerous applications; e.g. to generate training data for human pose estimation, in video games and in VR/AR. Our project page for data and code can be seen at: \url{https://vlg.inf.ethz.ch/projects/PSI/}.

Yan Zhang, Krikamol Muandet, Qianli Ma et al.

Fine-grained action segmentation in long untrimmed videos is an important task for many applications such as surveillance, robotics, and human-computer interaction. To understand subtle and precise actions within a long time period, second-order information (e.g. feature covariance) or higher is reported to be effective in the literature. However, extracting such high-order information is considerably non-trivial. In particular, the dimensionality increases exponentially with the information order, and hence gaining more representation power also increases the computational cost and the risk of overfitting. In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form. Specifically, our contributions are: (1) From the multilinear perspective, we derive a bilinear form of low complexity, assuming that the three-way tensor has low-rank frontal slices. (2) Rather than learning the tensor entries from data, we sample the entries from different underlying distributions, and prove that the underlying distribution influences the information order. (3) We employed our bilinear form as an intermediate layer in state-of-the-art deep neural networks, enabling to represent high-order information in complex deep models effectively and efficiently. Our experimental results demonstrate that the proposed bilinear form outperforms the previous state-of-the-art methods on the challenging temporal action segmentation task. One can see our project page for data, model and code: \url{https://vlg.inf.ethz.ch/projects/BilinearTCN/}.

Yan Zhang, Heiko Neumann

Detecting unintended falls is essential for ambient intelligence and healthcare of elderly people living alone. In recent years, deep convolutional nets are widely used in human action analysis, based on which a number of fall detection methods have been proposed. Despite their highly effective performances, the behaviors of how the convolutional nets recognize falls are still not clear. In this paper, instead of proposing a novel approach, we perform a systematical empirical study, attempting to investigate the underlying fall recognition process. We propose four tasks to investigate, which involve five types of input modalities, seven net instances and different training samples. The obtained quantitative and qualitative results reveal the patterns that the nets tend to learn, and several factors that can heavily influence the performances on fall recognition. We expect that our conclusions are favorable to proposing better deep learning solutions to fall detection systems.

Yan Zhang, Siyu Tang, Krikamol Muandet et al.

Fine-grained temporal action parsing is important in many applications, such as daily activity understanding, human motion analysis, surgical robotics and others requiring subtle and precise operations in a long-term period. In this paper we propose a novel bilinear pooling operation, which is used in intermediate layers of a temporal convolutional encoder-decoder net. In contrast to other work, our proposed bilinear pooling is learnable and hence can capture more complex local statistics than the conventional counterpart. In addition, we introduce exact lower-dimension representations of our bilinear forms, so that the dimensionality is reduced with neither information loss nor extra computation. We perform intensive experiments to quantitatively analyze our model and show the superior performances to other state-of-the-art work on various datasets.

Alex Bäuerle, Heiko Neumann, Timo Ropinski

Training data plays an essential role in modern applications of machine learning. However, gathering labeled training data is time-consuming. Therefore, labeling is often outsourced to less experienced users, or completely automated. This can introduce errors, which compromise valuable training data, and lead to suboptimal training results. We thus propose a novel approach that uses the power of pretrained classifiers to visually guide users to noisy labels, and let them interactively check error candidates, to iteratively improve the training data set. To systematically investigate training data, we propose a categorization of labeling errors into three different types, based on an analysis of potential pitfalls in label acquisition processes. For each of these types, we present approaches to detect, reason about, and resolve error candidates, as we propose measures and visual guidance techniques to support machine learning users. Our approach has been used to spot errors in well-known machine learning benchmark data sets, and we tested its usability during a user evaluation. While initially developed for images, the techniques presented in this paper are independent of the classification algorithm, and can also be extended to many other types of training data.

Yan Zhang, He Sun, Siyu Tang et al.

We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applicable in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of-the-art results for both online and offline settings.