Convolutional Filter

Convolutional filters are the fundamental building blocks of convolutional neural networks (CNNs), designed to extract features from data by applying learned weights to local regions. Current research focuses on improving filter design for robustness against adversarial attacks, enhancing interpretability through theory-driven filter structures and neurosymbolic approaches, and optimizing filter efficiency via techniques like factorization, pruning, and weight sharing, often within architectures such as ResNets, U-Nets, and transformers. These advancements are crucial for improving the accuracy, efficiency, and explainability of CNNs across diverse applications, including medical image analysis, speech recognition, and image restoration.

Papers

November 2, 2024

Convolutional Filtering with RKHS Algebras
Alejandro Parada-Mayorga, Leopoldo Agorio, Alejandro Ribeiro, Juan Bazerque
Reproducing Kernel Hilbert Space Convolutional Filter Signal Representation

October 8, 2024

UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters
Kovvuri Sai Gopal Reddy, Bodduluri Saran, A. Mudit Adityaja, Saurabh J. Shigwan, Nitin Kumar, Snehasis Mukherjee
Graph Neural Network Medical Image Segmentation Convolutional Filter Unsupervised Segmentation Unsupervised Image Segmentation

August 21, 2024

First line of defense: A robust first layer mitigates adversarial attacks
Janani Suresh, Nancy Nayak, Sheetal Kalyani
Adversarial Attack Adversarial Training Adversarial Learning Convolutional Filter Best Fit Line Adversarial Evaluation

August 13, 2024

A Theory-Based Explainable Deep Learning Architecture for Music Emotion
Hortense Fong, Vineet Kumar, K. Sudhir
Convolutional Neural Network Deep Learning Model Convolutional Filter Music Emotion Emotion Dynamic

July 15, 2024

Classification of Heart Sounds Using Multi-Branch Deep Convolutional Network and LSTM-CNN
Seyed Amir Latifi, Hassan Ghassemian, Maryam Imani
Classification Code Long Short Term Memory Convolutional Filter Automatic Diagnosis Human Heart Multi Branch

May 24, 2024

A Neurosymbolic Framework for Bias Correction in Convolutional Neural Networks
Parth Padalkar, Natalia Ślusarz, Ekaterina Komendantskaya, Gopal Gupta
Convolutional Neural Network Convolutional Filter Bias Correction Neurosymbolic Framework

March 26, 2024

Serpent: Scalable and Efficient Image Restoration via Multi-scale Structured State Space Models
Mohammad Shahab Sepehri, Zalan Fabian, Mahdi Soltanolkotabi
Multi Scale Image Restoration State Space Model Convolutional Filter Convolutional Neural Process High Resolution Image Restoration

March 12, 2024

Conditional computation in neural networks: principles and research trends
Simone Scardapane, Alessandro Baiocchi, Alessio Devoto, Valerio Marsocci, Pasquale Minervini, Jary Pomponi
Neural Network Mixture of Expert General Principle Convolutional Filter Research Trend Early Exit Neural Network Token Selection Conditional Computation

March 1, 2024

February 20, 2024

Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields
Bo-Yu Cheng, Wei-Chen Chiu, Yu-Lun Liu
Native Robustness Radiance Field Microbial Decomposition Camera Pose Joint Optimization Convolutional Filter 3D Convolution Tensorial Radiance Field

November 29, 2023

CRAFT: Contextual Re-Activation of Filters for face recognition Training
Aman Bhatta, Domingo Mery, Haiyu Wu, Kevin W. Bowyer
Face Recognition Convolutional Filter Max Filter Activation Map Traditional CrAFT CNN Backbone

November 24, 2023

Finding Foundation Models for Time Series Classification with a PreText Task
Ali Ismail-Fawaz, Maxime Devanne, Stefano Berretti, Jonathan Weber, Germain Forestier
Deep Learning Convolutional Neural Network Foundation Model Time Series Classification Convolutional Filter Pretext Task

November 6, 2023

Weight-Sharing Regularization
Mehran Shakerinava, Motahareh Sohrabi, Siamak Ravanbakhsh, Simon Lacoste-Julien
Deep Learning Convolutional Neural Network Convolutional Filter Weight Sharing

September 27, 2023

RSF-Conv: Rotation-and-Scale Equivariant Fourier Parameterized Convolution for Retinal Vessel Segmentation
Zihong Sun, Hong Wang, Qi Xie, Yefeng Zheng, Deyu Meng
Direct Convolution Convolutional Filter Retinal Vessel Segmentation Traditional Convolution F Net Probabilistic Equivariant Continuous Convolution

September 22, 2023

SPION: Layer-Wise Sparse Training of Transformer via Convolutional Flood Filling
Bokyeong Yoon, Yoonsang Han, Gordon Euhyun Moon
Transformer Based Convolutional Filter Sparse Training Sparse Transformer Fully Convolutional Sparse Pattern

August 22, 2023

Convoifilter: A case study of doing cocktail party speech recognition
Thai-Binh Nguyen, Alexander Waibel
Automatic Speech Recognition Case Study Speech Enhancement Speech Recognition System Convolutional Filter Multi Channel Multi Party Meeting Speech Enhancement Module

August 10, 2023

Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
Wencheng Han, Junbo Yin, Jianbing Shen
Monocular Depth Estimation Self Supervised Monocular Depth Estimation Convolutional Filter Depth Representation

July 12, 2023

YOGA: Deep Object Detection in the Wild with Lightweight Feature Learning and Multiscale Attention
Raja Sunkara, Tie Luo
Deep Learning Wild Challenge Convolutional Filter Deep Learning Based Object State of the Art Object Lightweight Object Detection Yoga Pose

June 22, 2023

Neural Network Pruning for Real-time Polyp Segmentation
Suman Sapkota, Pranav Poudel, Sudarshan Regmi, Bibek Panthi, Binod Bhattarai
Polyp Segmentation Convolutional Filter Neural Network Pruning Gradient Backpropagation Polyp Datasets