CNN Architecture

Convolutional Neural Networks (CNNs) are a cornerstone of computer vision, aiming to efficiently extract features from images for tasks like classification and object detection. Current research focuses on improving CNN efficiency through architectural innovations like structured ternary patterns, dynamic channel sampling, and novel pooling methods, as well as exploring the integration of CNNs with transformers to leverage both inductive biases and global context. These advancements are crucial for deploying CNNs on resource-constrained devices and enhancing their performance in various applications, from medical imaging to autonomous driving.

Papers

April 30, 2023

Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade
Convolutional Neural Network Comparative Study Feature Space CNN Architecture Interpretable Way CNN Performance Layer Similarity

April 23, 2023

Deep Convolutional Tables: Deep Learning without Convolutions
Shay Dekel, Yosi Keller, Aharon Bar-Hillel
Deep Learning Deep Network Direct Convolution Convolutional Layer CNN Architecture

April 11, 2023

Scale-Space Hypernetworks for Efficient Biomedical Imaging
Jose Javier Gonzalez Ortiz, John Guttag, Adrian Dalca
Convolutional Neural Network CNN Architecture Medical Image Analysis Task Photon Efficient Imaging

April 10, 2023

FreConv: Frequency Branch-and-Integration Convolutional Networks
Zhaowen Li, Xu Zhao, Peigeng Ding, Zongxin Gao, Yuting Yang, Ming Tang, Jinqiao Wang
High Frequency CNN Architecture Frequency Aware Convolution

April 3, 2023

Fine-tuning of explainable CNNs for skin lesion classification based on dermatologists' feedback towards increasing trust
Md Abdul Kadir, Fabrizio Nunnari, Daniel Sonntag
Neural Network Fine Tuning Human Feedback CNN Model CNN Architecture Skin Lesion

March 4, 2023

MetaGrad: Adaptive Gradient Quantization with Hypernetworks
Kaixin Xu, Alina Hui Xiu Lee, Ziyuan Zhao, Zhe Wang, Min Wu, Weisi Lin
Quantization Operator CNN Architecture Attention Hypernetworks Network Compression Gradient Quantization

February 21, 2023

Effects of Architectures on Continual Semantic Segmentation
Tobias Kalb, Niket Ahuja, Jingxing Zhou, Jürgen Beyerer
Mixed Effect Continual Learning CNN Architecture Architecture Perspective Continual Semantic Segmentation Incremental Semantic Segmentation

February 17, 2023

Low Latency Video Denoising for Online Conferencing Using CNN Architectures
Altanai Bisht, Ana Carolina de Souza Mendes, Justin David Thoreson, Shadrokh Samavi
Image Denoising CNN Architecture Video Denoising

February 13, 2023

February 12, 2023

Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia
Michail Chatzianastasis, Loukas Ilias, Dimitris Askounis, Michalis Vazirgiannis
Convolutional Neural Network Neural Architecture Search Alzheimer'S Disease Multimodal Fusion CNN Architecture Spontaneous Speech Dementia Detection

January 30, 2023

Convolutional Neural Network-Based Automatic Classification of Colorectal and Prostate Tumor Biopsies Using Multispectral Imagery: System Development Study
Remy Peyret, Duaa alSaeed, Fouad Khelifi, Nadia Al-Ghreimil, Heyam Al-Baity, Ahmed Bouridane
Deep Convolutional Neural Network CNN Model CNN Architecture Multispectral Image Automatic Classification Prostate Biopsy Prostate Cancer Whole Slide Image

January 26, 2023

The Power of Linear Combinations: Learning with Random Convolutions
Paul Gavrikov, Janis Keuper
Convolutional Neural Network Real Power CNN Architecture Convolutional Filter Linear Combination Convolution Based Random Convolution

January 6, 2023

Deep Learning For Classification Of Chest X-Ray Images (Covid 19)
Benbakreti Samir, Said Mwanahija, Benbakreti Soumia, Umut Özkaya
Deep Learning Classification Code Covid 19 Chest X Ray CNN Architecture Chest X Ray Image X Ray Image

January 1, 2023

GoogLe2Net: Going Transverse with Convolutions
Yuanpeng He
Convolutional Neural Network Direct Convolution Convolutional Layer CNN Architecture

December 30, 2022

December 17, 2022

FSCNN: A Fast Sparse Convolution Neural Network Inference System
Bo Ji, Tianyi Chen
Neural Network CNN Architecture Structured Sparsity Fast Convolution Sparse Convolutional

December 11, 2022

Estimator: An Effective and Scalable Framework for Transportation Mode Classification over Trajectories
Danlei Hu, Ziquan Fang, Hanxi Fang, Tianyi Li, Chunhui Shen, Lu Chen, Yunjun Gao
Handwritten Trajectory CNN Architecture Trajectory Data Linear Estimator Object Transportation Transportation Mode Parallel Transport

December 9, 2022

Music Recommendation System based on Emotion, Age and Ethnicity
Ramiz Mammadli, Huma Bilgin, Ali Can Karaca
Deep Learning Underlying Emotion Speech Based Age CNN Architecture Music Recommendation Facial Data