Kernel-blending connection approximated by a neural network for image classification

Liu, Xinxin; Zhang, Yunfeng; Bao, Fangxun; Kai, Shao; Sun, Ziyin; Zhang, Caiming

doi:10.1007/s41095-020-0181-9

Cited by 18 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we all know, almost all images have high information redundancy either in the form of low rank or sparse representation [11,12]: many pixels share similar features. Based on a low-rank prior or sparse representation, images can be denoised [13][14][15][16][17].…”

Section: Motivation and Contributionmentioning

confidence: 99%

Improved fuzzy clustering for image segmentation based on a low-rank prior

et al. 2021

Self Cite

View full text Add to dashboard Cite

Image segmentation is a basic problem in medical image analysis and useful for disease diagnosis. However, the complexity of medical images makes image segmentation difficult. In recent decades, fuzzy clustering algorithms have been preferred due to their simplicity and efficiency. However, they are sensitive to noise. To solve this problem, many algorithms using non-local information have been proposed, which perform well but are inefficient. This paper proposes an improved fuzzy clustering algorithm utilizing nonlocal self-similarity and a low-rank prior for image segmentation. Firstly, cluster centers are initialized based on peak detection. Then, a pixel correlation model between corresponding pixels is constructed, and similar pixel sets are retrieved. To improve efficiency and robustness, the proposed algorithm uses a novel objective function combining non-local information and a low-rank prior. Experiments on synthetic images and medical images illustrate that the algorithm can improve efficiency greatly while achieving satisfactory results.

show abstract

Section: Motivation and Contributionmentioning

confidence: 99%

Improved fuzzy clustering for image segmentation based on a low-rank prior

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the first problem, we decompose the image into two parts: the low frequency part representing the structure and the high frequency part containing the texture. In image super-resolution and image reconstruction, the high frequencies are usually considered to be the missing information in the scaling process used to refine the result [23][24][25].…”

Section: Global Sparse Decompositionmentioning

confidence: 99%

Image smoothing based on global sparsity decomposition and a variable parameter

Zhou

et al. 2021

Comp. Visual Media

Self Cite

View full text Add to dashboard Cite

Smoothing images, especially with rich texture, is an important problem in computer vision. Obtaining an ideal result is difficult due to complexity, irregularity, and anisotropicity of the texture. Besides, some properties are shared by the texture and the structure in an image. It is a hard compromise to retain structure and simultaneously remove texture. To create an ideal algorithm for image smoothing, we face three problems. For images with rich textures, the smoothing effect should be enhanced. We should overcome inconsistency of smoothing results in different parts of the image. It is necessary to create a method to evaluate the smoothing effect. We apply texture pre-removal based on global sparse decomposition with a variable smoothing parameter to solve the first two problems. A parametric surface constructed by an improved Bessel method is used to determine the smoothing parameter. Three evaluation measures: edge integrity rate, texture removal rate, and gradient value distribution are proposed to cope with the third problem. We use the alternating direction method of multipliers to complete the whole algorithm and obtain the results. Experiments show that our algorithm is better than existing algorithms both visually and quantitatively. We also demonstrate our method’s ability in other applications such as clip-art compression artifact removal and content-aware image manipulation.

show abstract

“…We select three classical datasets, i.e., CIFAR-10 [15], CIFAR-100 [15] and UC-M [16] for our experiments. The datasets CIFAR-10 and CIFAR-100 are both 32×32 color images, containing 10 and 100 categories respectively.…”

Section: Simulation Experiments Analysismentioning

confidence: 99%

Multi-Attention Ghost Residual Fusion Network for Image Classification

Jia

Guo

et al. 2021

IEEE Access

View full text Add to dashboard Cite

In order to achieve high-efficiency and high-precision multi-image classification tasks, a multi-attention ghost residual fusion network (MAGR) is proposed. MAGR is formed by cascading basic feature extraction network (BFE), ghost residual mapping network (GRM) and image classification network (IC). The BFE uses spatial and channel attention mechanisms to help the MAGR extract low-level features of the input image in a targeted manner. The GRM is formed by cascading 4 multi-branch group convolutional ghost residual blocks (MGR-Blocks). Each MGR-Block is cascaded by a dimension reducer and several ghost residual sub-networks (GRSs). The GRS integrates ghost convolution and residual connection, and the use of ghost convolution can significantly reduce parameters and achieve high-efficient classification. The GRS is a parallel convolution structure with 32 branches, which ensures that GRM has enough width to extract advanced features and extract as much feature information as possible, so as to obtain high-precision classification. The IC completes the aggregation of high-dimensional channel feature information, and then achieves a significant improvement in the classification accuracy of MAGR, by fusing the effective channel attention mechanism, global average pooling and SoftMax layer. Simulation experiment shows that MAGR has excellent classification capability while achieving high efficiency and lightweight. Compare with VGG16, the parameters of MAGR on CIFAR-10 is reduced by 94.8% while the classification accuracy is increased by 1.18%. Compare with MobileNetV2, the parameters of MAGR on CIFAR-100 is reduced by 33.9% while the classification accuracy is increased by 15.6%.

show abstract

Kernel-blending connection approximated by a neural network for image classification

Cited by 18 publications

References 25 publications

Improved fuzzy clustering for image segmentation based on a low-rank prior

Improved fuzzy clustering for image segmentation based on a low-rank prior

Image smoothing based on global sparsity decomposition and a variable parameter

Multi-Attention Ghost Residual Fusion Network for Image Classification

Contact Info

Product

Resources

About