paper-with-me

홈 › Papers

DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer

2022-11-15 · Hongyi Pan, Xin Zhu, Salih Atici, Ahmet Enis Cetin

In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the $3\times3$ Conv2D layers in the Residual neural Network (ResNet). Convolutional filtering operations are performed in the DCT domain using element-wise multiplications by taking advantage of the Fourier and DCT Convolution theorems. A trainable soft-thresholding layer is used as the nonlinearity in the DCT perceptron. Compared to ResNet's Conv2D layer which is spatial-agnostic and channel-specific, the proposed layer is location-specific and channel-specific. The DCT-perceptron layer reduces the number of parameters and multiplications significantly while maintaining comparable accuracy results of regular ResNets in CIFAR-10 and ImageNet-1K. Moreover, the DCT-perceptron layer can be inserted with a batch normalization layer before the global average pooling layer in the conventional ResNets as an additional layer to improve classification accuracy.

📄 PDF Abstract BibTeX arXiv:2211.08577

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Average Pooling 설명 없음
Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets

2023-03-13 · Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Salih Atici 외

In this paper, we propose a set of transform-based neural network layers as an alternative to the $3\times3$ Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogon…

A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional Layer

2023-05-27 · Hongyi Pan, Xin Zhu, Salih Atici, Ahmet Enis Cetin

In this paper, we propose a novel Hadamard Transform (HT)-based neural network layer for hybrid quantum-classical computing. It implements the regular convolutional layers in the Hadamard transform domain. The idea is ba…

WavPool: A New Block for Deep Neural Networks

2023-06-14 · Samuel D. McDermott, M. Voetberg, Brian Nord

Modern deep neural networks comprise many operational layers, such as dense or convolutional layers, which are often collected into blocks. In this work, we introduce a new, wavelet-transform-based network architecture t…

Vision Conformer: Incorporating Convolutions into Vision Transformer Layers

2023-04-27 · Brian Kenji Iwana, Akihiro Kusuda

Transformers are popular neural network models that use layers of self-attention and fully-connected nodes with embedded tokens. Vision Transformers (ViT) adapt transformers for image recognition tasks. In order to do th…

Inductive BiasLanguage ModelingLanguage Modelling

Convolution in Convolution for Network in Network

2016-03-22 · Yanwei Pang, Manli Sun, Xiaoheng Jiang, Xuelong. Li

Network in Netwrok (NiN) is an effective instance and an important extension of Convolutional Neural Network (CNN) consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for c…