KO | EN

GitLite

Minimalist Open Source Repository Search Engine

gitlite — search

#dsh #dsh-plugin #developer-tools #ai-agent #claude-code #codex #typescript #ai-agents #deepseek-harness #mcp #cli #rust

GENet

★ 229 Open GitHub ↗

No description available.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks ([paper](https://papers.nips.cc/paper/8151-gather-excite-exploiting-feature-context-in-convolutional-neural-networks.pdf))
By Jie Hu[1], Li Shen[2], Samuel Albanie[2], Gang Sun[1], Andrea Vedaldi[2].

[Momenta](https://momenta.ai/)[1] and [University of Oxford](http://www.robots.ox.ac.uk/~vgg/)[2].

## Approach
<div align="center">
 <img src="https://github.com/hujie-frank/GENet/blob/master/figures/GE-module.jpg">
</div>

 Figure 1: The Diagram of a Gather-Excite module.

<div align="center">
 <img src="https://github.com/hujie-frank/GENet/blob/master/figures/GEPF8.jpg" width="420" height="480">
 <img src="https://github.com/hujie-frank/GENet/blob/master/figures/GEPF.jpg" width="400" height="480">
 <img src="https://github.com/hujie-frank/GENet/blob/master/figures/GEP8.jpg" width="460" height="480">
 <img src="https://github.com/hujie-frank/GENet/blob/master/figures/GEP.jpg" width="400" height="480">
</div>

 Figure 2: The Schema of Gather-Excite modules. Top-left: $GE-\theta^-\,(E8)$. Top-right: $GE-\theta^-$. Bottom-left: $GE-\theta\,(E8)$. Bottom-right: $GE-\theta$.

## Implementation
In this repository, all the models are implemented by [Caffe](https://github.com/BVLC/caffe).
 
We use the data augmentation strategies with our previous work [SENet](https://github.com/hujie-frank/SENet).

There are three new layers introduced for efficient training and inference, these are *Axpy*, *DepthwiseConvolution* and *CuDNNBatchNorm* layers.  
+ The [*Axpy*](https://github.com/hujie-frank/SENet/blob/master/src/caffe/layers/) layer is already implemented in [SENet](https://github.com/hujie-frank/SENet).
+ As for [*DepthwiseConvolution*](https://github.com/yonghenglh6/DepthwiseConvolution/tree/master/caffe/src/caffe/layers) layer, it is publicly avaliable at the [repo](https://github.com/yonghenglh6/DepthwiseConvolution/), or you can directly replace it with the standard *Convolution* layer if you don't care about the operational efficiency.

## Trained Models
Coming soon!

## Citation

If you use Gather-Excite in your research, please cite the paper:
    
    @inproceedings{hu2018genet,
      title={Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks},
      author={Jie Hu and Li Shen and Samuel Albanie and Gang Sun and Andrea Vedaldi},
      journal={NeurIPS},
      year={2018}
    }

GENet

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README