Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Convolutional Neural Networks with Alternately Updated Clique (to appear in CVPR 2018)
| Date | Stars |
|---|---|
| 2026-07-24 | 327 |
| 2026-07-25 | 327 |
| 2026-07-28 | 327 |
| 2026-07-30 | 327 |
| 2026-07-31 | 327 |
| 2026-08-06 | 327 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# CliqueNet
This repository is for [Convolutional Neural Networks with Alternately Updated Clique](https://arxiv.org/abs/1802.10419) (to appear in CVPR 2018, Oral presentation),
by Yibo Yang, Zhisheng Zhong, Tiancheng Shen, and [Zhouchen Lin](http://www.cis.pku.edu.cn/faculty/vision/zlin/zlin.htm).
### citation
If you find CliqueNet useful in your research, please consider citing:
@article{yang18,
author={Yibo Yang and Zhisheng Zhong and Tiancheng Shen and Zhouchen Lin},
title={Convolutional Neural Networks with Alternately Updated Clique},
journal={arXiv preprint arXiv:1802.10419},
year={2018}
}
### table of contents
- [Introduction](#introduction)
- [Usage](#usage)
- [Ablation experiments](#ablation-experiments)
- [Comparison with state of the arts](#comparision-with-state-of-the-arts)
- [Results on ImageNet](#results-on-imagenet)
## Introduction
CliqueNet is a newly proposed convolutional neural network architecture where any pair of layers in the same block are connected bilaterally (Fig 1). Any layer is both the input and output another one, and information flow can be maximized. During propagation, the layers are updated alternately (Fig 2), so that each layer will always receive the feedback information from the layers that are updated more lately. We show that the refined features are more discriminative and lead to a better performance. On benchmark classification datasets including CIFAR-10, CIFAR-100, SVHN, and ILSVRC 2012, we achieve better or comparable results over state of the arts with fewer parameters. This repo contains the code of our project, and also provides some experimental results that are out of the paper.
<div align=left><img src="https://raw.githubusercontent.com/iboing/CliqueNet/master/img/fig1.JPG" width="40%" height="40%">
Fig 1. An illustration of a block with 4 layers. Node 0 denotes the input layer of this block.
<div align=left><img src="https://raw.githubusercontent.com/iboing/CliqueNet/master/img/tab1.JPG" width="55%" height="55%">
Fig 2. Alternate updating rule in CliqueNet. "{}" denotes the concatenating operator.
## Usage
- Our experiments are conducted with [TensorFlow](https://github.com/tensorflow/tensorflow) in Python 2.
- Clone this repo: `git clone https://github.com/iboing/CliqueNet`
- An example to train a model on CIFAR or SVHN:
```bash
python train.py --gpu [gpu id] --dataset [cifar-10 or cifar-100 or SVHN] --k [filters per layer] --T [all layers of three blocks] --dir [path to save models]
```
- Additional techniques (optional): if you want to use attentional transition, bottleneck architecture, or compression strategy in our paper, add `--if_a True`, `--if_b True`, and `--if_c True`, respectively.
## Ablation experiments
With the feedback connections, CliqueNet alternately re-update previous layers with updated layers, to enable refined features. The weights among layers are re-used for multiple times, so that a deeper representation space can be attained with a fixed number of parameters. In order to test the effectiveness of CliqueNet's feature refinement, we analyze the features generated in different stages by conducting experiments using different versions of CliqueNet. As illustrated by Fig 3, the CliqueNet(I+I) only uses Stage-I feature. The CliqueNet(I+II) uses Stage-I feature concatenated with input layer as the block feature, but transits Stage-II feature into the next block. The CliqueNet(II+II) only uses refined features.
<div align=left><img src="https://raw.githubusercontent.com/iboing/CliqueNet/master/img/fig3.JPG" width="55%" height="55%">
Fig 3. A schema for CliqueNet(i+j), i,j belong to {I,II}.
|Model |block feature |transit |error(%)|
|-----------------|-----------------|--------|--------|
|CliqueNet(I+I) |{ X_0, Stage-I } |Stage-I |6.64 |
|CliqueNet(I+II) |{ X_0, Stage-I } |Stage-II|6.10 |
|CliqueNet(II+II) |{ X_0, Stage-II }|Stage-II|5.76 |
Tab 1. Resutls of different versions of CliqueNets.
To Excerpt of 7,463 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0196069e624cc6b3, topic:deep-learning
matched fp:0196069e624cc6b3, topic:computer-vision