Synthetic Data for the Analysis of Archival Documents: Handwriting Determination.Bartz, Christian; Seidel, Laurenz; Nguyen, Duy-Hung; Bethge, Joseph; Yang, Haojin; Meinel, Christoph (2020).
Automatic Matching of Paintings and Descriptions in Art-Historic Archives using Multimodal Analysis.Bartz, Christian; Jain, Nitisha; Krestel, Ralf (2020). 23--28.
BMXNet 2: An Open Source Framework for Low-bit Networks-Reproducing, Understanding, Designing and Showcasing.Bethge, Joseph; Bartz, Christian; Yang, Haojin; Meinel, Christoph (2020). 4469--4472.
AbstractRecently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also show the simplicity of creating a new dataset, based on a few videos (e.g. downloaded from YouTube) and artificially generated data.
LoANs: Weakly Supervised Object Detection with Localizer Assessor Networks.Bartz, Christian; Yang, Haojin; Bethge, Joseph; Meinel, Christoph (2018). 341--356.
Language Identification Using Deep Convolutional Recurrent Neural Networks.Bartz, Christian; Herold, Tom; Yang, Haojin; Meinel, Christoph D. Liu, Xie, S., Li, Y., Zhao, D., El-Alfy, E. -S. M. (reds.) (2017). 880--889.
HerausgeberLiu, Derong and Xie, Shengli and Li, Yuanqing and Zhao, Dongbin and El-Alfy, El-Sayed M.
AbstractLanguage Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without automatic language detection, speech utterances cannot be parsed correctly and grammar rules cannot be applied, causing subsequent speech recognition steps to fail. We propose a LID system that solves the problem in the image domain, rather than the audio domain. We use a hybrid Convolutional Recurrent Neural Network (CRNN) that operates on spectrogram images of the provided audio snippets. In extensive experiments we show, that our model is applicable to a range of noisy scenarios and can easily be extended to previously unknown languages, while maintaining its classification accuracy. We release our code and a large scale training set for LID systems to the community.
Language Identification Using Deep Convolutional Recurrent Neural Networks.Bartz, Christian; Herold, Tom; Yang, Haojin; Meinel, Christoph (2017).
BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet.Yang, Haojin; Fritzsche, Martin; Bartz, Christian; Meinel, Christoph in MM '17 (2017).
