Fakultät Informatik und Wirtschaftsinformatik
Refine
Year of publication
Document Type
- Conference Proceeding (147)
- Article (117)
- Part of a Book (14)
- Book (11)
- Bachelor Thesis (1)
- Doctoral Thesis (1)
- Part of Periodical (1)
- Working Paper (1)
Keywords
- Gamification (2)
- Informationssicherheit (2)
- data (2)
- informationssicherheit (2)
- Apps (1)
- Artificial Intelligence (1)
- Autistic (1)
- Autonomous Toy (1)
- Autonomous vehicles (1)
- BDSG (1)
Diffusion-based Visual Counterfactual Explanations - Towards Systematic Quantitative Evaluation
(2023)
Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. In this work, we propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used. We use this framework to explore the effects of certain crucial design choices in the latest diffusion-based generative models for VCEs of natural image classification (ImageNet). We conduct a battery of ablation-like experiments, generating thousands of VCEs for a suite of classifiers of various complexity, accuracy and robustness. Our findings suggest multiple directions for future advancements and improvements of VCE methods. By sharing our methodology and our approach to tackle the computational challenges of such a study on a limited hardware setup (including the complete code base), we offer a valuable guidance for researchers in the field fostering consistency and transparency in the assessment of counterfactual explanations.
In this work, we addresses the problem of modeling distributions of graphs. We introduce the Vector-Quantized Graph Auto-Encoder (VQ-GAE), a permutation-equivariant discrete auto-encoder and designed to model the distribution of graphs. By exploiting the permutation-equivariance of graph neural networks (GNNs), our autoencoder circumvents the problem of the ordering of the graph representation. We leverage the capability of GNNs to capture local structures of graphs while employing vector-quantization to prevent the mapping of discrete objects to a continuous latent space. Furthermore, the use of autoregressive models enables us to capture the global structure of graphs via the latent representation. We evaluate our model on standard datasets used for graph generation and observe that it achieves excellent performance on some of the most salient evaluation metrics compared to the state-of-the-art.
One of the most discussed issues in graph generative modeling is the ordering of the representation. One solution consists of using equivariant generative functions, which ensure the ordering invariance. After having discussed some properties of such functions, we propose 3G-GAN, a 3-stages model relying on GANs and equivariant functions. The model is still under development. However, we present some encouraging exploratory experiments and discuss the issues still to be addressed.
This article describes an approach for mobile robots to identify scenes in configurations of objects spread across dense environments. This identification is enabled by intertwining the robotic object search and the scene recognition on already detected objects. We proposed “Implicit Shape Model (ISM) trees” as a scene model to solve these two tasks together. This article presents novel algorithms for ISM trees to recognize scenes and predict object poses. For us, scenes are sets of objects, some of which are interrelated by 3D spatial relations. Yet, many false positives may occur when using single ISMs to recognize scenes. We developed ISM trees, which is a hierarchical model of multiple interconnected ISMs, to remedy this. In this article, we contribute a recognition algorithm that allows the use of these trees for recognizing scenes. ISM trees should be generated from human demonstrations of object configurations. Since a suitable algorithm was unavailable, we created an algorithm for generating ISM trees. In previous work, we integrated the object search and scene recognition into an active vision approach that we called “Active Scene Recognition”. An efficient algorithm was unavailable to make their integration using predicted object poses effective. Physical experiments in this article show that the new algorithm we have contributed overcomes this problem.
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features. We follow the strategy of implicit distribution modelling via generative adversarial network (GAN) combined with permutation equivariant message passing architecture operating over the sets of nodes and edges. This enables generating the feature vectors of all the graph objects in one go (in 2 phases) as opposed to a much slower one-by-one generations of sequential models, prevents the need for expensive graph matching procedures usually needed for likelihood-based generative models, and uses efficiently the network capacity by being insensitive to the particular node ordering in the graph representation. To the best of our knowledge, this is the first method that models the feature distribution along the graph skeleton allowing for generations of annotated graphs with user specified structures. Our experiments demonstrate the ability of our model to learn complex structured distributions through quantitative evaluation over three annotated graph datasets.
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features. We follow the strategy of implicit distribution modelling via generative adversarial network (GAN) combined with permutation equivariant message passing architecture operating over the sets of nodes and edges. This enables generating the feature vectors of all the graph objects in one go (in 2 phases) as opposed to a much slower one-by-one generations of sequential models, prevents the need for expensive graph matching procedures usually needed for likelihood-based generative models, and uses efficiently the network capacity by being insensitive to the particular node ordering in the graph representation. To the best of our knowledge, this is the first method that models the feature distribution along the graph skeleton allowing for generations of annotated graphs with user specified structures. Our experiments demonstrate the ability of our model to learn complex structured distributions through quantitative evaluation over three annotated graph datasets.
Comparison of 2.4 GHz WiFi FTM- and RSSI-Based Indoor Positioning Methods in Realistic Scenarios
(2020)