Related papers: Frequency Pooling: Shift-Equivalent and Anti-Alias…
Graph Neural Networks (GNNs) have shown significant success for graph-based tasks. Motivated by the prevalence of large datasets in real-world applications, pooling layers are crucial components of GNNs. By reducing the size of input…
Traditional vision transformer consists of two parts: transformer encoder and multi-layer perception (MLP). The former plays the role of feature learning to obtain better representation, while the latter plays the role of classification.…
Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in several state-of-the-art CNNs. Global average pooling or…
Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. However, these networks, which rely on parameter sharing and discrete…
Convolutional Neural Networks have become the standard for image classification tasks, however, these architectures are not invariant to translations of the input image. This lack of invariance is attributed to the use of stride which…
A key problem in blind image quality assessment (BIQA) is how to effectively model the properties of human visual system in a data-driven manner. In this paper, we propose a simple and efficient BIQA model based on a novel framework which…
The pooling operation is a cornerstone element of convolutional neural networks. These elements generate receptive fields for neurons, in which local perturbations should have minimal effect on the output activations, increasing robustness…
Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing…
Downsampling layers, including pooling and strided convolutions, are crucial components of the convolutional neural network architecture that determine both the granularity/scale of image feature analysis as well as the receptive field size…
The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. However, these methods may ignore the underlying distribution of…
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated…
Supervised learning-based methods yield robust denoising results, yet they are inherently limited by the need for large-scale clean/noisy paired datasets. The use of unsupervised denoisers, on the other hand, necessitates a more detailed…
Recent works have demonstrated that global covariance pooling (GCP) has the ability to improve performance of deep convolutional neural networks (CNNs) on visual classification task. Despite considerable advance, the reasons on…
Channel pruning is widely used to reduce the complexity of deep network models. Recent pruning methods usually identify which parts of the network to discard by proposing a channel importance criterion. However, recent studies have shown…
For many years, it has been shown how much exploiting equivariances can be beneficial when solving image analysis tasks. For example, the superiority of convolutional neural networks (CNNs) compared to dense networks mainly comes from an…
A weakly-supervised semantic segmentation framework with a tied deconvolutional neural network is presented. Each deconvolution layer in the framework consists of unpooling and deconvolution operations. 'Unpooling' upsamples the input…
Recently, the generalization behavior of Convolutional Neural Networks (CNN) is gradually transparent through explanation techniques with the frequency components decomposition. However, the importance of the phase spectrum of the image for…
Covariance pooling is a feature pooling method with good classification accuracy. Because covariance features consist of second-order statistics, the scale of the feature elements are varied. Therefore, normalizing covariance features using…
Convolution operations dominate the overall execution time of Convolutional Neural Networks (CNNs). This paper proposes an easy yet efficient technique for both Convolutional Neural Network training and testing. The conventional convolution…
Convolutional neural networks (CNN) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete grid into a reduced grid with the same connectivity and…