Large-scale object recognition with CUDA-accelerated hierarchical neural networks
By Rafael Uetz, Sven Behnke. 2009
91 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- J. Urgen Schmidhuber
- Yoshua Bengio
- Sergey Levine
- Lior Wolf
- Pieter Abbeel
- Quoc V. Le
- Mohit Bansal
- Adam Coates
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Andrew Zisserman
- Xiaogang Wang
- Andrea Vedaldi
- Ming-Hsuan Yang
- Jitendra Malik
Citations in the corpus
- High-Performance Neural Networks for Visual Object Classification (2011, methodology): “On MNIST the best network achieved a recognition test error rate of 0.35%, on NORB 2.53% and on CIFAR10 19.51%.”
- Large-Scale Deep Learning on the YFCC100M Dataset (2015, background): “Deep neural networks applied to natural images have demonstrated state-of-the-art performance in supervised object recognition tasks [10, 1] as well as unsupervised neural networks [2, 3].”
- A committee of neural networks for traffic sign classification (2011, background): “Most previous GPU-based CNN implementations [11], [12] were hard-coded to satisfy GPU hardware constraints, whereas ours is flexible and fully online (i.e., weight updates after each image).”
- HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation (2020, background): “Such layers played an important role in the early days of deep learning, mostly due to computational reasons [10, 36, 47].”
- An Analysis of Single-Layer Networks in Unsupervised Feature Learning (2011, unknown): “6%) Deep neural network [27] 97.”
- Multi-column deep neural networks for image classification (2012, background): “Carefully designed GPU code for image classification can be up to two orders of magnitude faster than its CPU counterpart [35, 34].”
- The German Traffic Sign Recognition Benchmark: A multi-class classification competition (2011, background): “With respect to other implementations of similar neural network architectures on GPUs [11], [12] that are hard-coded to satisfy the hardware constraints of the GPUs, our implementation [13] is flexible and fully on-line (i.”
- Deep learning with COTS HPC systems (2013, background): “Buoyed by many empirical successes (Uetz & Behnke, 2009; Raina et al., 2009; Ciresan et al., 2012; Krizhevsky, 2010; Coates et al., 2011) much deep learning research has focused on the goal of building larger models with more parameters.”