Refine
Year of publication
Document Type
- Conference Proceeding (19)
- Article (8)
- Part of a Book (3)
- Doctoral Thesis (3)
- Master's Thesis (2)
- Bachelor Thesis (1)
- Book (1)
- Preprint (1)
- Report (1)
Keywords
- 3D ship detection (1)
- Bayesian convolutional neural networks (1)
- Calibration procedure (1)
- Classification (1)
- Computer vision (1)
- Convolutional networks (1)
- Crowdmanagement (1)
- Deep Transformation Model (1)
- Deep learning (4)
- Defect detection (1)
- Didaktik (2)
- Environmental perception (1)
- Extended object tracking (1)
- Extension estimation (1)
- Finite-element (1)
- Forest establishment (1)
- Freistellungssemesterbericht (1)
- GPU (1)
- Gaussian processes (1)
- Ground detection (1)
- Image novelty detection (1)
- Imaging (1)
- Interpretability (1)
- Inverse perspective (1)
- Ischemic stroke (1)
- Learning to cluster (1)
- LernApp (1)
- Lidar (2)
- Lidar-camera registration (1)
- Machine Learning (1)
- Machine learning (1)
- Magnetic resonance imaging (1)
- Mashine learning (1)
- Mask R-CNN (1)
- Mathematik (1)
- Mean-shift (1)
- Mirror (1)
- Mobile robot (1)
- Modelling (1)
- Multi-camera (1)
- Multivariate Differentiation (1)
- Mutual information (1)
- Normalizing Flow (1)
- Object detection (1)
- Pedestrian (1)
- Perceptual grouping (1)
- Personenstromsimulation (1)
- Probabilistic modeling (1)
- Random matrices (1)
- Real-time (1)
- Reconstruction (1)
- Recurrent neural network (1)
- Regression (1)
- Screening (1)
- Seamless Learning (2)
- Segmentation (1)
- Sensor fusion (1)
- Ship dataset (1)
- Speaker clustering (1)
- Speaker recognition (1)
- Speech & image clustering (1)
- Statistics (1)
- Stereo-matching (1)
- Surrogate Modell (1)
- Tree seedlings (1)
- Un-certainty (1)
- Uncertainty (1)
- Unmanned aerial vehicles (1)
Institute
- Institut für Optische Systeme - IOS (39) (remove)
Fast and reliable acquisition of truth data for document analysis using cyclic suggest algorithms
(2019)
In document analysis the availability of ground truth data plays a crucial role for the success of a project. This is even more true at the rise of new deep learning methods which heavily rely on the availability of training data. But even for traditional, hand crafted algorithms that are not trained on data, reliable test data is important for the improvement and evaluation of the methods. Because ground truth acquisition is expensive and time consuming, semi-automatic methods are introduced which make use of suggestions coming from document analysis systems. The interaction between the human operator and the automatic analysis algorithms is the key to speed up the process while improving the quality of the data. The final confirmation of data may always be done by the human operator. This paper demonstrates a use case for acquisition of truth data in a mail processing system. It shows why a new, extended view on truth data is necessary in development and engineering of such systems. An overview over the tool and the data handling is given, the advantages in the workflow are shown, and consequences for the construction of analysis algorithms are discussed. It can be shown that the interplay between suggest algorithms and human operator leads to very fast truth data capturing. The surprising finding is the fact that if multiple suggest algorithms circularly depend on data, they are especially effective in terms of speed and accuracy.
Pascal Laube presents machine learning approaches for three key problems of reverse engineering of defective structured surfaces: parametrization of curves and surfaces, geometric primitive classification and inpainting of high-resolution textures. The proposed methods aim to improve the reconstruction quality while further automating the process. The contributions demonstrate that machine learning can be a viable part of the CAD reverse engineering pipeline.
Deep neural networks have become a veritable alternative to classic speaker recognition and clustering methods in recent years. However, while the speech signal clearly is a time series, and despite the body of literature on the benefits of prosodic (suprasegmental) features, identifying voices has usually not been approached with sequence learning methods. Only recently has a recurrent neural network (RNN) been successfully applied to this task, while the use of convolutional neural networks (CNNs) (that are not able to capture arbitrary time dependencies, unlike RNNs) still prevails. In this paper, we show the effectiveness of RNNs for speaker recognition by improving state of the art speaker clustering performance and robustness on the classic TIMIT benchmark. We provide arguments why RNNs are superior by experimentally showing a “sweet spot” of the segment length for successfully capturing prosodic information that has been theoretically predicted in previous work.
We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each 1≤k≤kmax, a distribution over the individual cluster assignment for each data point. The network is trained in advance in a supervised fashion on separate data to learn grouping by any perceptual similarity criterion based on pairwise labels (same/different group). It can then be applied to different data containing different groups. We demonstrate promising performance on high-dimensional data like images (COIL-100) and speech (TIMIT). We call this “learning to cluster” and show its conceptual difference to deep metric learning, semi-supervise clustering and other related approaches while having the advantage of performing learnable clustering fully end-to-end.
Rheumatoid arthritis is an autoimmune disease that causes chronic inflammation of synovial joints, often resulting in irreversible structural damage. The activity of the disease is evaluated by clinical examinations, laboratory tests, and patient self-assessment. The long-term course of the disease is assessed with radiographs of hands and feet. The evaluation of the X-ray images performed by trained medical staff requires several minutes per patient. We demonstrate that deep convolutional neural networks can be leveraged for a fully automated, fast, and reproducible scoring of X-ray images of patients with rheumatoid arthritis. A comparison of the predictions of different human experts and our deep learning system shows that there is no significant difference in the performance of human experts and our deep learning model.
Multi-Dimensional Connectionist Classification is amethod for weakly supervised training of Deep Neural Networksfor segmentation-free multi-line offline handwriting recognition.MDCC applies Conditional Random Fields as an alignmentfunction for this task. We discuss the structure and patterns ofhandwritten text that can be used for building a CRF. Since CRFsare cyclic graphical models, we have to resort to approximateinference when calculating the alignment of multi-line text duringtraining, here in the form of Loopy Belief Propagation. This workconcludes with experimental results for transcribing small multi-line samples from the IAM Offline Handwriting DB which showthat MDCC is a competitive methodology.