Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Hees, Jörn"'
Anomaly detection in real-world scenarios poses challenges due to dynamic and often unknown anomaly distributions, requiring robust methods that operate under an open-world assumption. This challenge is exacerbated in practical settings, where models
Externí odkaz:
http://arxiv.org/abs/2404.14933
This paper addresses the classification of Arabic text data in the field of Natural Language Processing (NLP), with a particular focus on Natural Language Inference (NLI) and Contradiction Detection (CD). Arabic is considered a resource-poor language
Externí odkaz:
http://arxiv.org/abs/2307.14666
We present new Recurrent Neural Network (RNN) cells for image classification using a Neural Architecture Search (NAS) approach called DARTS. We are interested in the ReNet architecture, which is a RNN based approach presented as an alternative for co
Externí odkaz:
http://arxiv.org/abs/2304.05838
Autor:
Moser, Brian, Raue, Federico, Frolov, Stanislav, Hees, Jörn, Palacio, Sebastian, Dengel, Andreas
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research e.g., allowing flexible upsampling, more effecti
Externí odkaz:
http://arxiv.org/abs/2209.13131
Recent advances in Explainable AI (XAI) increased the demand for deployment of safe and interpretable AI models in various industry sectors. Despite the latest success of deep neural networks in a variety of domains, understanding the decision-making
Externí odkaz:
http://arxiv.org/abs/2209.10658
Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes and corre
Externí odkaz:
http://arxiv.org/abs/2204.02035
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Neural Architecture Search (NAS) defines the design of Neural Networks as a search problem. Unfortunately, NAS is computationally intensive because of various possibilities depending on the number of elements in the design and the possible connection
Externí odkaz:
http://arxiv.org/abs/2203.06905
Autor:
Azimi, Fatemeh, Nies, Jean-Francois Jacques Nicolas, Palacio, Sebastian, Raue, Federico, Hees, Jörn, Dengel, Andreas
Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy. The main concept in curriculum l
Externí odkaz:
http://arxiv.org/abs/2108.09696
Spatial Transformer Networks (STN) can generate geometric transformations which modify input images to improve the classifier's performance. In this work, we combine the idea of STN with Reinforcement Learning (RL). To this end, we break the affine t
Externí odkaz:
http://arxiv.org/abs/2106.14295
In the past, the rapidly evolving field of sound classification greatly benefited from the application of methods from other domains. Today, we observe the trend to fuse domain-specific tasks and approaches together, which provides the community with
Externí odkaz:
http://arxiv.org/abs/2106.13043