convolutional neural networks
Convolutional neural networks (CNNs) are a class of deep learning models particularly effective for processing grid-like data, such as images. They utilize convolutional layers to automatically identify and learn spatial hierarchies and features within image data, making them foundational for computer vision tasks.
- AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
- CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs
- Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification
- DAMamba: Vision State Space Model with Dynamic Adaptive Scan
- DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
- Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
- G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks
- ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
- ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
- Locality in Image Diffusion Models Emerges from Data Statistics
- MobileODE: An Extra Lightweight Network
- Normalize Filters! Classical Wisdom for Deep Vision
- STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology
- STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex
- Sinusoidal Initialization, Time for a New Start
- Structured Initialization for Vision Transformers
- The Quest for Universal Master Key Filters in DS-CNNs
- msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML