Are sparse representations really relevant for image classification?
2016-08-03 17:01
381 查看
Roberto Rigamonti, Matthew A.Brown, Vincent Lepetit
CVLab, EPFL
The result:
no advantages is gained by imposing sparsity at run-time, at least when this sparsity is not tailored in a discriminative fashion.
Sparsity constaints: <- evidence for sparse representations in th mammal brain
Predictive Sparse Decomposition:an endeavor to avoid the sparsity optimization by learning a regressor that approximates the
optimal reconstruction.
1. extract features by using filters which are either learned or handcrafted: Olshausen and Field's algorihm(OLS)
M dictionary, t 坐标
上式只能用在small patches of images, 在large image 上时需要对M同时进行优化。因此改成卷积形式。
f:filters t: images with the same size of x
using stochastic gradient descent with clipping to optimize the filters and t
get the filters-> for each image, caculate t:
three methods:two optimizing method and one convolutional method
2. apply a non-linear operation to the features
ABS or Relu
3.pool the features to obtain robustness to small translations and deformations
Gaussian pooling(Gauss)/average pooling(Boxcar)/Maximum value pooling (MAX)
4. Classification
Nearest neighbor classification(NN)
support vector machines(SVM)
5. Result:
5.1 Recognition rate drops dramatically as sparsity increases when computing features.
5.2A strong sparsity is important in learning the feature extractors, but harmful during classification.
5.3 Increasing sparsity helps in the denoising of Gaussian noise, but fails in the case of structured noise.As in latter case , it focuses on the noisy area, and ignores the area with meaningful information
5.4 In architectures that employ pooling stages, sparsity is therefore a temporary condition only. The results after pooling are dense.
CVLab, EPFL
The result:
no advantages is gained by imposing sparsity at run-time, at least when this sparsity is not tailored in a discriminative fashion.
Sparsity constaints: <- evidence for sparse representations in th mammal brain
Predictive Sparse Decomposition:an endeavor to avoid the sparsity optimization by learning a regressor that approximates the
optimal reconstruction.
1. extract features by using filters which are either learned or handcrafted: Olshausen and Field's algorihm(OLS)
M dictionary, t 坐标
上式只能用在small patches of images, 在large image 上时需要对M同时进行优化。因此改成卷积形式。
f:filters t: images with the same size of x
using stochastic gradient descent with clipping to optimize the filters and t
get the filters-> for each image, caculate t:
three methods:two optimizing method and one convolutional method
2. apply a non-linear operation to the features
ABS or Relu
3.pool the features to obtain robustness to small translations and deformations
Gaussian pooling(Gauss)/average pooling(Boxcar)/Maximum value pooling (MAX)
4. Classification
Nearest neighbor classification(NN)
support vector machines(SVM)
5. Result:
5.1 Recognition rate drops dramatically as sparsity increases when computing features.
5.2A strong sparsity is important in learning the feature extractors, but harmful during classification.
5.3 Increasing sparsity helps in the denoising of Gaussian noise, but fails in the case of structured noise.As in latter case , it focuses on the noisy area, and ignores the area with meaningful information
5.4 In architectures that employ pooling stages, sparsity is therefore a temporary condition only. The results after pooling are dense.
相关文章推荐
- 关于2009_CVPR_Linear spatial pyramid matching using sparse coding for image classification
- Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification代码解
- Linear Spatial Pyramid Matching Using Sparse Coding for Image Classification 理解
- Linear Spatial Pyramid Matching using Sparse Coding for Image Classification (阅读)
- HCP: A Flexible CNN Framework for Multi-label Image Classification论文学习
- 笔记:Learning Fast Low-Rank Projection for Image Classification
- 论文阅读:Joint Learning of Single-image and Cross-image Representations for Person Re-identification
- 1607.CVPR-Joint Learning of Single-image and Cross-image Representations for Person ReID 论文笔记
- 《Sparse and Redundant Representations:From Theory to Applications in Signal and Image Processing》序论
- Multi-column deep neural networks for image classification阅读
- 【读论文】Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification
- 《PCANet: A Simple Deep Learning Baseline for Image Classification》精读笔记
- Andrew Ng 深度学习课程Deeplearning.ai 编程作业——deep Neural network for image classification(1-4.2)
- 《PCANet: A Simple Deep Learning Baseline for Image Classification》
- Geometric Lp-norm Feature Pooling for Image Classification
- 多标签图像分类--HCP: A Flexible CNN Framework for Multi-Label Image Classification
- 多柱深度神经网络——Multi-column Deep Neural Networks for Image Classification
- Task-Driven Feature Pooling for Image Classification(一种监督的pooling方法——TDFpooling)
- Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification