Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
Image-based 6-DoF pose estimation of arbitrarily shaped 3D objects based on their shape is a rarely studied problem. Most existing image-based methods for pose estimation either exploit textural information in form of local features or, if shape-based, rely on the extraction of straight line segments or other primitives. Straight-forward extensions of 2D approaches are potentially more general, but in practice assume a limited range of possible view angles. The general problem is that a 3D object can potentially produce completely different 2D projections depending on its relative pose to the observing camera. One way to reduce the solution space is to exploit temporal information, i.e. perform tracking. Again, existing model-based tracking approaches rely on relatively simple object geometries. In this paper, we propose a particle filter based tracking approach that can deal with arbitrary shapes and arbitrary or even no texture, i.e. it offers a general solution to the rigid object tracking problem. As our approach can deal with occlusions, it is in particular of interest in the context of goal-directed imitation learning involving the observation of object manipulations. Results of simulation experiments as well as real-world experiments with different object types prove the practical applicability of our approach
Although computer vision and other machine perception have made great progress in recent years, corresponding high-level components have not progressed that fast. We present a general purpose framework for high-level situation recognition that is suited for arbitrary application domains and sensor setups. Our approach is hierarchical as opposed to monolithic and we focus on modeling expert knowledge with Fuzzy Metric Temporal Logic and Situation Graph Trees rather than learning from training data. To demonstrate the power and flexibility of our approach, we present case studies in two different settings: guiding the operator's attention in video surveillance and automatic report generation in smart environments. Our results show that this approach can yield a conceptually exhaustive situation recognition for diverse input modalities and application domains.
This contribution aims at assisting video surveillance operators with automatic understanding of situations in videos. The situations comprise many different agents interacting in groups. To this end we extended an existing situation recognition framework based on Situation Graph Trees and Fuzzy Metric Temporal Logic. Non-parametric meanshift clustering is utilized to support the logic-based inference process for such group-based situations, namely to improve efficiency. Additionally, the underlying knowledge base was augmented to also handle multiagent queries and the situation inference was adapted to also handle inference for group-based situations. For evaluation the publicly available BEHAVE video dataset was used consisting of partially annotated real video data of persons. The results show that the proposed system is capable of correctly and efficiently understanding such group-based situations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.