Doubly Convolutional Neural Networks
Authors: Shuangfei Zhai, Yu Cheng, Zhongfei (Mark) Zhang, Weining Lu
NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform extensive experiments on three image classification benchmarks: CIFAR-10, CIFAR-100 and Image Net, and show that DCNNs consistently outperform other competing architectures. |
| Researcher Affiliation | Collaboration | Shuangfei Zhai Binghamton University Vestal, NY 13902, USA szhai2@binghamton.edu Yu Cheng IBM T.J. Watson Research Center Yorktown Heights, NY 10598, USA chengyu@us.ibm.com Weining Lu Tsinghua University Beijing 10084, China luwn14@mails.tsinghua.edu.cn Zhongfei (Mark) Zhang Binghamton University Vestal, NY 13902, USA zhongfei@cs.binghamton.edu |
| Pseudocode | Yes | Algorithm 1: Implementation of double convolution with convolution. |
| Open Source Code | No | The paper does not provide any explicit statements about open-source code availability or links to repositories. |
| Open Datasets | Yes | We conduct several sets of experiments with DCNN on three image classification benchmarks: CIFAR-10, CIFAR-100, and Image Net. |
| Dataset Splits | Yes | CIFAR-10 and CIFAR-100 both contain 50,000 training and 10,000 testing 32 32 sized RGB images... Image Net is the dataset used in the ILSVRC-2012 challenge, which consists of about 1.2 million images for training and 50,000 images for validation, sampled from 1,000 classes. |
| Hardware Specification | Yes | All the models are trained with Adadelta [21] on NVIDIA K40 GPUs. |
| Software Dependencies | No | The paper mentions 'Theano which is used in our experiments' but does not provide a specific version number for Theano or any other software dependencies. |
| Experiment Setup | Yes | Bath size is set as 200 for CIFAR-10 and CIFAR-100, and 128 for Image Net. ... Our model design is similar to VGGNet [2] where 3 3 filter sizes are used... Zero padding is used before each convolutional layer... Dropout is applied after each pooling layer. ... The full specification of the model architectures is shown in Table 1. |