Caffe: Convolutional Architecture for Fast Feature Embedding
By Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross B. Girshick, Sergio Guadarrama, Trevor Darrell. 2014
14,879 citations recorded by the source corpus.
Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Caffe fits industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU (approx 2 ms per image). By separating model representation from actual implementation, Caffe allows experimentation and seamless switching among platforms for ease of development and deployment from prototyping machines to cloud environments. Caffe is maintained and developed by the Berkeley Vision and Learning Center (BVLC) with the help of an active community of contributors on GitHub. It powers ongoing research projects, large-scale industrial applications, and startup prototypes in vision, speech, and multimedia.
Subfields: Computer Vision and Pattern Recognition, Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Xiaogang Wang
- Trevor Darrell
- Jitendra Malik
- Yi Yang
- Andrew Zisserman
In Model Architectures
- Quoc V. Le
- Yoshua Bengio
- Alan L. Yuille
- Kaiming He
- Xiaogang Wang
- Chunhua Shen
- Trevor Darrell
- Dacheng Tao
Citations in the corpus
- Deep Residual Learning for Image Recognition (2015, positive): “, Caffe [19]) without modifying the solvers.”
- How transferable are features in deep neural networks? (2014, methodology): “Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093.”
- Training Very Deep Networks (2015, methodology): “Some experiments were conducted using the Caffe [31] library.”
- Fast R-CNN (2015, methodology): “No disk storage is required for feature caching Fast R-CNN is written in Python and C++ (Caffe [12]) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn .”
- Fully convolutional networks for semantic segmentation (2014, methodology): “Implementation All models are trained and tested with Caffe [16] on a single NVIDIA Tesla K40c.”
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019, background): “computer vision [Oquab et al., 2014; Jia et al., 2014; Huh et al., 2016; Yosinski et al., 2014]) use a supervised dataset for pre-training, we were interested to see whether omitting the unsupervised task from the multi-task pre-training mixture still produced good results.”
- U-Net: Convolutional Networks for Biomedical Image Segmentation (2015, methodology): “The Netherlands. full Caffe[6]-based implementation and the trained networks4.”
- Mixed Precision Training (2017, methodology): “Networks were trained using Caffe (Jia et al., 2014) framework modified to use Volta TensorOps.”
- PyTorch: An Imperative Style, High-Performance Deep Learning Library (2019, methodology): “Many popular frameworks such as Caffe [1], CNTK [2], TensorFlow [3], and Theano [4], construct a static dataflow graph that represents the computation and which can then be applied repeatedly to batches of data.”
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2018, positive): “Evaluation was performed using Caffe (Jia et al., 2014).”
- Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, positive): “In this experiment we evaluate how good are the learned visual features of the 6 layer CNN (CaffeNet) for image classification when trained with the self-supervised method explained in Section 3.”
- TensorFlow: A system for large-scale machine learning (2016, neutral): “Extensibility Single-machine machine learning frameworks [36, 2, 17] have extensible programming models that enable their users to advance the state of the art with new approaches, such as adversarial learning [25] and deep reinforcement learning [51].”
- Webly Supervised Learning of Convolutional Networks (2015, methodology): “For fair comparison, we use the same architecture (besides the output layer) as the BLVC reference network [23], which is a slight variant of of the original network proposed by [24].”