Refine
H-BRS Bibliography
- yes (65)
Departments, institutes and facilities
- Fachbereich Informatik (65) (remove)
Document Type
- Conference Object (23)
- Article (18)
- Preprint (9)
- Report (4)
- Book (monograph, edited volume) (2)
- Part of a Book (2)
- Conference Proceedings (2)
- Research Data (2)
- Doctoral Thesis (2)
- Master's Thesis (1)
Year of publication
- 2022 (65) (remove)
Keywords
Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. For underwater robotics, it is of great interest to design computer vision algorithms to improve perception capabilities such as sonar image classification. Due to the confidential nature of sonar imaging and the difficulty to interpret sonar images, it is challenging to create public large labeled sonar datasets to train supervised learning algorithms. In this work, we investigate the potential of three self-supervised learning methods (RotNet, Denoising Autoencoders, and Jigsaw) to learn high-quality sonar image representation without the need of human labels. We present pre-training and transfer learning results on real-life sonar image datasets. Our results indicate that self-supervised pre-training yields classification performance comparable to supervised pre-training in a few-shot transfer learning setup across all three methods. Code and self-supervised pre-trained models are be available at https://github.com/agrija9/ssl-sonar-images
We introduce canonical weight normalization for convolutional neural networks. Inspired by the canonical tensor decomposition, we express the weight tensors in so-called canonical networks as scaled sums of outer vector products. In particular, we train network weights in the decomposed form, where scale weights are optimized separately for each mode. Additionally, similarly to weight normalization, we include a global scaling parameter. We study the initialization of the canonical form by running the power method and by drawing randomly from Gaussian or uniform distributions. Our results indicate that we can replace the power method with cheaper initializations drawn from standard distributions. The canonical re-parametrization leads to competitive normalization performance on the MNIST, CIFAR10, and SVHN data sets. Moreover, the formulation simplifies network compression. Once training has converged, the canonical form allows convenient model-compression by truncating the parameter sums.
Vietnam requires a sustainable urbanization, for which city sensing is used in planning and de-cision-making. Large cities need portable, scalable, and inexpensive digital technology for this purpose. End-to-end air quality monitoring companies such as AirVisual and Plume Air have shown their reliability with portable devices outfitted with superior air sensors. They are pricey, yet homeowners use them to get local air data without evaluating the causal effect. Our air quality inspection system is scalable, reasonably priced, and flexible. Minicomputer of the sys-tem remotely monitors PMS7003 and BME280 sensor data through a microcontroller processor. The 5-megapixel camera module enables researchers to infer the causal relationship between traffic intensity and dust concentration. The design enables inexpensive, commercial-grade hardware, with Azure Blob storing air pollution data and surrounding-area imagery and pre-venting the system from physically expanding. In addition, by including an air channel that re-plenishes and distributes temperature, the design improves ventilation and safeguards electrical components. The gadget allows for the analysis of the correlation between traffic and air quali-ty data, which might aid in the establishment of sustainable urban development plans and poli-cies.
Comparative study of 3D object detection frameworks based on LiDAR data and sensor fusion techniques
(2022)
Estimating and understanding the surroundings of the vehicle precisely forms the basic and crucial step for the autonomous vehicle. The perception system plays a significant role in providing an accurate interpretation of a vehicle's environment in real-time. Generally, the perception system involves various subsystems such as localization, obstacle (static and dynamic) detection, and avoidance, mapping systems, and others. For perceiving the environment, these vehicles will be equipped with various exteroceptive (both passive and active) sensors in particular cameras, Radars, LiDARs, and others. These systems are equipped with deep learning techniques that transform the huge amount of data from the sensors into semantic information on which the object detection and localization tasks are performed. For numerous driving tasks, to provide accurate results, the location and depth information of a particular object is necessary. 3D object detection methods, by utilizing the additional pose data from the sensors such as LiDARs, stereo cameras, provides information on the size and location of the object. Based on recent research, 3D object detection frameworks performing object detection and localization on LiDAR data and sensor fusion techniques show significant improvement in their performance. In this work, a comparative study of the effect of using LiDAR data for object detection frameworks and the performance improvement seen by using sensor fusion techniques are performed. Along with discussing various state-of-the-art methods in both the cases, performing experimental analysis, and providing future research directions.
Recent advances in Natural Language Processing have substantially improved contextualized representations of language. However, the inclusion of factual knowledge, particularly in the biomedical domain, remains challenging. Hence, many Language Models (LMs) are extended by Knowledge Graphs (KGs), but most approaches require entity linking (i.e., explicit alignment between text and KG entities). Inspired by single-stream multimodal Transformers operating on text, image and video data, this thesis proposes the Sophisticated Transformer trained on biomedical text and Knowledge Graphs (STonKGs). STonKGs incorporates a novel multimodal architecture based on a cross encoder that uses the attention mechanism on a concatenation of input sequences derived from text and KG triples, respectively. Over 13 million so-called text-triple pairs, coming from PubMed and assembled using the Integrated Network and Dynamical Reasoning Assembler (INDRA), were used in an unsupervised pre-training procedure to learn representations of biomedical knowledge in STonKGs. By comparing STonKGs to an NLP- and a KG-baseline (operating on either text or KG data) on a benchmark consisting of eight fine-tuning tasks, the proposed knowledge integration method applied in STonKGs was empirically validated. Specifically, on tasks with a comparatively small dataset size and a larger number of classes, STonKGs resulted in considerable performance gains, beating the F1-score of the best baseline by up to 0.083. Both the source code as well as the code used to implement STonKGs are made publicly available so that the proposed method of this thesis can be extended to many other biomedical applications.
Contextual information is widely considered for NLP and knowledge discovery in life sciences since it highly influences the exact meaning of natural language. The scientific challenge is not only to extract such context data, but also to store this data for further query and discovery approaches. Classical approaches use RDF triple stores, which have serious limitations. Here, we propose a multiple step knowledge graph approach using labeled property graphs based on polyglot persistence systems to utilize context data for context mining, graph queries, knowledge discovery and extraction. We introduce the graph-theoretic foundation for a general context concept within semantic networks and show a proof of concept based on biomedical literature and text mining. Our test system contains a knowledge graph derived from the entirety of PubMed and SCAIView data and is enriched with text mining data and domain-specific language data using Biological Expression Language. Here, context is a more general concept than annotations. This dense graph has more than 71M nodes and 850M relationships. We discuss the impact of this novel approach with 27 real-world use cases represented by graph queries. Storing and querying a giant knowledge graph as a labeled property graph is still a technological challenge. Here, we demonstrate how our data model is able to support the understanding and interpretation of biomedical data. We present several real-world use cases that utilize our massive, generated knowledge graph derived from PubMed data and enriched with additional contextual data. Finally, we show a working example in context of biologically relevant information using SCAIView.
State-of-the-art object detectors are treated as black boxes due to their highly non-linear internal computations. Even with unprecedented advancements in detector performance, the inability to explain how their outputs are generated limits their use in safety-critical applications. Previous work fails to produce explanations for both bounding box and classification decisions, and generally make individual explanations for various detectors. In this paper, we propose an open-source Detector Explanation Toolkit (DExT) which implements the proposed approach to generate a holistic explanation for all detector decisions using certain gradient-based explanation methods. We suggests various multi-object visualization methods to merge the explanations of multiple objects detected in an image as well as the corresponding detections in a single image. The quantitative evaluation show that the Single Shot MultiBox Detector (SSD) is more faithfully explained compared to other detectors regardless of the explanation methods. Both quantitative and human-centric evaluations identify that SmoothGrad with Guided Backpropagation (GBP) provides more trustworthy explanations among selected methods across all detectors. We expect that DExT will motivate practitioners to evaluate object detectors from the interpretability perspective by explaining both bounding box and classification decisions.
21 pages, with supplementary