Convolutional Neural Network
Convolutional Neural Networks (CNNs) are a class of deep learning models designed for processing grid-like data, excelling in image analysis and related tasks. Current research focuses on improving CNN efficiency and robustness, exploring architectures like EfficientNet and Swin Transformers, as well as novel approaches such as Mamba models to address limitations in computational cost and long-range dependency capture. This active field of research has significant implications across diverse applications, including medical image analysis (e.g., cancer detection, Alzheimer's diagnosis), damage assessment, and art forgery detection, demonstrating the power of CNNs for automating complex visual tasks.
Papers
Generalization Enhancement Strategies to Enable Cross-year Cropland Mapping with Convolutional Neural Networks Trained Using Historical Samples
Sam Khallaghi, Rahebe Abedi, Hanan Abou Ali, Hamed Alemohammad, Mary Dziedzorm Asipunu, Ismail Alatise, Nguyen Ha, Boka Luo, Cat Mai, Lei Song, Amos Wussah, Sitian Xiong, Yao-Ting Yao, Qi Zhang, Lyndon D. Estes
Layer-Specific Optimization: Sensitivity Based Convolution Layers Basis Search
Vasiliy Alekseev, Ilya Lukashevich, Ilia Zharikov, Ilya Vasiliev
Optimizing Vision Transformers with Data-Free Knowledge Transfer
Gousia Habib, Damandeep Singh, Ishfaq Ahmad Malik, Brejesh Lall
Derivation of Back-propagation for Graph Convolutional Networks using Matrix Calculus and its Application to Explainable Artificial Intelligence
Yen-Che Hsiao, Rongting Yue, Abhishek Dutta
TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Dataflow and Analytical Modelling
Cristian Sestito, Shady Agwa, Themis Prodromakis