paper-with-me

Papers

Residual Feature-Reutilization Inception Network for Image Classification

2024-12-27 · Yuanpeng He, Wenjie Song, Lijian Li, Tianxiang Zhan, Wenpin Jiao

Capturing feature information effectively is of great importance in the field of computer vision. With the development of convolutional neural networks (CNNs), concepts like residual connection and multiple scales promote continual performance gains in diverse deep learning vision tasks. In this paper, we propose a novel CNN architecture that it consists of residual feature-reutilization inceptions (ResFRI) or split-residual feature-reutilization inceptions (Split-ResFRI). And it is composed of four convolutional combinations of different structures connected by specially designed information interaction passages, which are utilized to extract multi-scale feature information and effectively increase the receptive field of the model. Moreover, according to the network structure designed above, Split-ResFRI can adjust the segmentation ratio of the input information, thereby reducing the number of parameters and guaranteeing the model performance. Specifically, in experiments based on popular vision datasets, such as CIFAR10 ($97.94$\%), CIFAR100 ($85.91$\%) and Tiny Imagenet ($70.54$\%), we obtain state-of-the-art results compared with other modern models under the premise that the model size is approximate and no additional data is used.

📄 PDF Abstract BibTeX arXiv:2412.19433

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

GoogLe2Net: Going Transverse with Convolutions

2023-01-01 · Yuanpeng He

Capturing feature information effectively is of great importance in vision tasks. With the development of convolutional neural networks (CNNs), concepts like residual connection and multiple scales promote continual perf…

image-classificationImage Classificationvalid

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

2016-02-23 · Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi

Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance …

ClassificationGeneral ClassificationImage Classification

Classifying galaxies in the Galaxy10 DECals dataset using Inception and Residual CNNs

2026-06-07 · Lanz Anthonee A. Lagman, Prospero C. Naval, Reinabelle C. Reyes arxiv

Image data regarding galactic morphology is expected to increase both in quantity and quality for the next foreseeable years; thus it is important to explore which deep learning architectures adapted for image classifica…

Computational EfficiencyImage Classification

Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural Network

2018-11-10 · Md Zahangir Alom, Chris Yakopcic, Tarek M. Taha, Vijayan K. Asari

The Deep Convolutional Neural Network (DCNN) is one of the most powerful and successful deep learning approaches. DCNNs have already provided superior performance in different modalities of medical imaging including brea…

Cancer ClassificationClassificationGeneral ClassificationObject Recognition

Skin Cancer Segmentation and Classification with NABLA-N and Inception Recurrent Residual Convolutional Networks

2019-04-25 · Md Zahangir Alom, Theus Aspiras, Tarek M. Taha, Vijayan K. Asari

In the last few years, Deep Learning (DL) has been showing superior performance in different modalities of biomedical image analysis. Several DL architectures have been proposed for classification, segmentation, and dete…

Cancer ClassificationClassificationGeneral ClassificationImage Segmentation+4