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

February 23, 2024

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
Abolfazl Younesi, Mohsen Ansari, MohammadAmin Fazli, Alireza Ejlali, Muhammad Shafique, Jörg Henkel
Deep Learning Convolutional Neural Network Technical Challenge Financial Application Direct Convolution CNN Architecture Future Trend Different Convolutional Neural Network 3D Convolutional Neural Network

February 19, 2024

Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
Shubhi Shukla, Manaar Alam, Pabitra Mitra, Debdeep Mukhopadhyay
Adversarial Example Transfer Learning Generative Adversarial CNN Architecture Convolutional Neural Network Model Adversarial Image Side Channel

February 13, 2024

Peeking Behind the Curtains of Residual Learning
Tunhou Zhang, Feng Yan, Hai Li, Yiran Chen
CNN Architecture Residual Connection Residual Learning Light Curtain Plain Neural

January 24, 2024

CNN architecture extraction on edge GPU
Peter Horvath, Lukasz Chmielewski, Leo Weissbart, Lejla Batina, Yuval Yarom
CNN Architecture Side Channel Extraction Attack Jetson Nano

December 12, 2023

XC-NAS: A New Cellular Encoding Approach for Neural Architecture Search of Multi-path Convolutional Neural Networks
Trevor Londt, Xiaoying Gao, Peter Andreae, Yi Mei
Neural Architecture Search CNN Architecture Multi Path Performant Neural Network Population Encoding

November 20, 2023

PhytNet -- Tailored Convolutional Neural Networks for Custom Botanical Data
Jamie R. Sykes, Katherine Denby, Daniel W. Franks
Computer Vision CNN Architecture Infrared Image Crop Classification

November 18, 2023

NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search
Zhenrong Wang, Bin Li, Weifeng Li, Shuanlong Niu, Wang Miao, Tongzhi Niu
Neural Network Deep Convolutional Neural Network Neural Architecture Search CNN Architecture Surface Defect Detection Adaptive Design

November 13, 2023

PadChannel: Improving CNN Performance through Explicit Padding Encoding
Juho Kim
Convolutional Neural Network CNN Architecture Zero Padding CNN Performance

November 1, 2023

Revealing CNN Architectures via Side-Channel Analysis in Dataflow-based Inference Accelerators
Hansika Weerasena, Prabhat Mishra
CNN Architecture Side Channel CNN Accelerator Dataflow Based

October 18, 2023

Learning to Generate Parameters of ConvNets for Unseen Image Data
Shiye Wang, Kaituo Feng, Changsheng Li, Ye Yuan, Guoren Wang
LeArning Abstract Many Parameter CNN Architecture High Performing 1D ConvNet Unseen Data

September 24, 2023

Evolution of Convolutional Neural Network (CNN): Compute vs Memory bandwidth for Edge AI
Dwith Chenna
Convolutional Neural Network Memory Trace CNN Network CNN Architecture CNN Performance Edge Artificial Intelligence

September 22, 2023

Targeted Activation Penalties Help CNNs Ignore Spurious Signals
Dekai Zhang, Matthew Williams, Francesca Toni
Convolutional Neural Network CNN Architecture Targeted Activation Penalty Random Telegraph Signal

September 7, 2023

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications
Jiatai Lin, Guoqiang Han, Xuemiao Xu, Changhong Liang, Tien-Tsin Wong, C. L. Philip Chen, Zaiyi Liu, Chu Han
Semantic Segmentation Weakly Supervised CNN Architecture Class Activation Wide Angle Small Training

September 5, 2023

Traffic Light Recognition using Convolutional Neural Networks: A Survey
Svetlana Pavlitska, Nico Lambing, Ashok Kumar Bangaru, J. Marius Zöllner
Convolutional Neural Network Timely Survey CNN Architecture Traffic Light

August 16, 2023

KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution
Chao Li, Anbang Yao
CNN Architecture High Performing 1D ConvNet Kernel Extension Dynamic Convolution

July 25, 2023

A signal processing interpretation of noise-reduction convolutional neural networks
Luis A. Zavala-Mondragón, Peter H. N. de With, Fons van der Sommen
Deep Learning CNN Model CNN Architecture Signal Processing Framelet Transform

July 24, 2023

Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold
Pourya Shamsolmoali, Masoumeh Zareapoor
CNN Architecture Convolution Operation Image Transformation Spatial Transformer Network Learning Approach Interpolation Method Transformer Based Entropy Model Tangent Bundle

July 19, 2023

Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition
Jia-Xin Zhuang, Jiabin Cai, Jianguo Zhang, Wei-shi Zheng, Ruixuan Wang
Medical Image Classification Medical Image Datasets Region Specific CNN Architecture True Class Imbalanced Medical Image Lesion Image

May 16, 2023

Deep Ensembling for Perceptual Image Quality Assessment
Nisar Ahmed, H. M. Shahzad Asif, Abdul Rauf Bhatti, Atif Khan
Image Quality Image Quality Assessment CNN Architecture Model Ensembling Blind Image Quality Assessment

May 7, 2023

RATs-NAS: Redirection of Adjacent Trails on GCN for Neural Architecture Search
Yu-Ming Zhang, Jun-Wei Hsieh, Chun-Chieh Lee, Kuo-Chin Fan
Neural Architecture Search Neural Network Architecture CNN Architecture Root to Leaf Path Unknown Out of Domain