# Bilinear Pooling: Package extension of MatConvNet
Created by Tsung-Yu Lin, Aruni RoyChowdhury and Subhransu Maji at UMass Amherst
### Introduction
This repository contains the code implemting bilinear pooling proposed in our ICCV 2015 paper:
@inproceedings{lin2015bilinear,
Author = {Tsung-Yu Lin, Aruni RoyChowdhury, and Subhransu Maji},
Title = {Bilinear CNNs for Fine-grained Visual Recognition},
Booktitle = {International Conference on Computer Vision (ICCV)},
Year = {2015}
}
The code is tested on Ubuntu 14.04 using NVIDIA K40 GPU and MATLAB R2014b.
Link to the [project page](http://vis-www.cs.umass.edu/bcnn).
### Installation
This code is the extension to support bilinear pooling on [MatConvNet](http://www.vlfeat.org/matconvnet).Follow instructions on MatConvNet pages to install it first. Our code is built on MatConvNet version `1.0-beta18`. To retrieve a particular version of MatConvNet using git type:
>> git fetch --tags
>> git checkout tags/v1.0-beta18
The code implements the bilinear combination layer in symmetic and assymetic CNNs and contains scripts to fine-tune models and run experiments on several fine-grained recognition datasets. We also provide pre-trained models.
### Usage
The package provides following functions:
For simplenn:
1. **vl_nnbilinearpool**
The implementation of pooling self-outer product across locations to get an image descriptor. The function is called in *vl_bilinearnn* when the layer has field `type='bilinearpool'`.
2. **vl_nnbilinearclpool**
The function takes two features maps x1 and x2 as input and computer the outer product between features which are pooled across locations to form an image descriptor. The function is called in *vl_bilinearnn* when the layer has field `type='bilinearclpool'`.
3. **vl_nnsqrt**
The function normalize features using square root normalization for every location. The function is called in *vl_bilinearnn* when the layer has field `type='sqrt'`.
4. **vl_nnl2norm**:
The function normalize features using l2 normalization for every location. The function is called in *vl_bilinearnn* when the layer has field `type='l2norm'`.
5. **vl_bilinearnn**: Similar to vl_simplenn but with support of above layers. The function is used to compute forward and backward passes through a netwrok.
For DagNN:
1. **BilinearClPooling**
Dagnn bilinear pooling layer taking two set of features as input and computing the outer product followed by sum pooling.
2. **BilinearPooling**
Dagnn bilinear pooling layer taking features as input and computing the self outer product followed by sum pooling.
3. SquareRoot
Dagnn square root normalization layer
4. L2Norm
Dagnn L2 normalization layer
### Acknowldgements
We thank MatConvNet and VLFEAT teams for creating and maintaining these excellent packages.
没有合适的资源?快使用搜索试试~ 我知道了~
DBCNN:使用深双线性卷积神经网络进行盲图像质量评估
共174个文件
mat:111个
m:51个
txt:7个
5星 · 超过95%的资源 需积分: 50 14 下载量 48 浏览量
2021-02-02
17:30:44
上传
评论 2
收藏 6.28MB ZIP 举报
温馨提示
DBCNN:使用深双线性卷积神经网络进行盲图像质量评估
资源详情
资源评论
资源推荐
收起资源包目录
DBCNN:使用深双线性卷积神经网络进行盲图像质量评估 (174个子文件)
LICENSE 4KB
LICENSE 2KB
LICENSE 1KB
vl_simplenn.m 18KB
initializeNetworkTwoStreams2.m 17KB
initializeNetworkTwoStreams.m 16KB
bcnn_train_simplenn.m 14KB
vl_bilinearnn.m 14KB
bcnn_train_dag.m 11KB
imdb_cnn_train.m 11KB
initializeNetworkSharedWeights.m 10KB
imdb_bcnn_train_dag.m 8KB
getCsiqDatabase_train.m 6KB
model_setup.m 6KB
imdb_get_batch_bcnn.m 6KB
net_deploy.m 6KB
initializeNetFromEncoder.m 6KB
randnd.m 4KB
distortion_generator.m 3KB
vl_nnbilinearclpool.m 3KB
getLiveDatabase_train.m 3KB
vl_nnbilinearcl.m 3KB
imdb_get_batch.m 3KB
adam.m 2KB
run_exp.m 2KB
run_experiments_bcnn_train.m 2KB
savefast.m 2KB
getMLIVEDatabase_train.m 2KB
PDist.m 2KB
getTIDDatabase_train.m 2KB
BilinearPooling.m 2KB
find_bestmodel.m 2KB
vl_nnbilinear.m 1KB
vl_nnbilinearpool.m 1KB
Bilinear.m 1KB
BilinearClPooling.m 1KB
vl_nnl2norm.m 1KB
saturate.m 1KB
print_dataset_info.m 1KB
vl_nnsqrt.m 1KB
verify_performance.m 1KB
getBatchDagNNWrapper.m 989B
SquareRoot.m 968B
L2Norm.m 955B
getCliveDatabase_train.m 918B
getBatchSimpleNNWrapper.m 779B
demo.m 635B
encoder_save.m 395B
deploy_each_dagnet.m 388B
net_move_to_device.m 257B
logistic.m 251B
loadState_deploy.m 192B
setup.m 188B
setup.m 20B
scnn.mat 2.29MB
imdb-seed-1.mat 111KB
imdb-seed-1.mat 111KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 80KB
imdb-seed-1.mat 47KB
imdb-seed-1.mat 47KB
imdb-seed-1.mat 45KB
imdb-seed-1.mat 45KB
imdb-seed-1.mat 38KB
imdb-seed-1.mat 38KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
imdb-seed-1.mat 37KB
共 174 条
- 1
- 2
吃肥皂吐泡沫
- 粉丝: 28
- 资源: 4587
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论1