1 code implementation • 23 Nov 2022 • Nianhui Guo, Joseph Bethge, Christoph Meinel, Haojin Yang
In this work, we revisit the potential of binary neural networks and focus on a compelling but unanswered problem: how can a binary neural network achieve the crucial accuracy level (e. g., 80%) on ILSVRC-2012 ImageNet?
no code implementations • 29 Sep 2021 • Nianhui Guo, Joseph Bethge, Haojin Yang, Kai Zhong, Xuefei Ning, Christoph Meinel, Yu Wang
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts, often based on specialized model designs using additional 32-bit components.
1 code implementation • 13 Jun 2021 • Nianhui Guo, Joseph Bethge, Haojin Yang, Kai Zhong, Xuefei Ning, Christoph Meinel, Yu Wang
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts.
1 code implementation • 21 Oct 2020 • Christian Bartz, Joseph Bethge, Haojin Yang, Christoph Meinel
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks.
1 code implementation • 16 Jan 2020 • Joseph Bethge, Christian Bartz, Haojin Yang, Ying Chen, Christoph Meinel
However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks.
1 code implementation • 19 Nov 2019 • Christian Bartz, Joseph Bethge, Haojin Yang, Christoph Meinel
Most of these methods propose novel building blocks for neural networks.
no code implementations • 19 Jun 2019 • Joseph Bethge, Haojin Yang, Marvin Bornstein, Christoph Meinel
Binary Neural Networks (BNNs) show promising progress in reducing computational and memory costs but suffer from substantial accuracy degradation compared to their real-valued counterparts on large-scale datasets, e. g., ImageNet.
1 code implementation • 5 Dec 2018 • Joseph Bethge, Marvin Bornstein, Adrian Loy, Haojin Yang, Christoph Meinel
In our work, we focus on increasing the performance of binary neural networks without such prior knowledge and a much simpler training strategy.
1 code implementation • 14 Nov 2018 • Christian Bartz, Haojin Yang, Joseph Bethge, Christoph Meinel
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.
1 code implementation • 27 Sep 2018 • Joseph Bethge, Haojin Yang, Christian Bartz, Christoph Meinel
In our work, we focus on increasing our understanding of the training process and making it accessible to everyone.