Convolutional Backbone

Convolutional backbones are the foundational feature extraction components of many deep learning models, primarily used in computer vision tasks. Current research emphasizes improving their efficiency, often by integrating transformer blocks to leverage both local and global contextual information, leading to architectures like LowFormer that prioritize real-world throughput and latency. This focus on efficiency and the exploration of hybrid CNN-transformer models is driven by the need for faster and more resource-efficient solutions across diverse applications, from medical image analysis to autonomous driving. The resulting advancements significantly impact various fields by enabling more accurate and practical deployments of deep learning systems.

Papers

September 5, 2024

LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones
Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni
Backbone Fine Tuning Low Frequency Convolutional Backbone Efficient Hardware Vision Backbone Backbone Network

May 22, 2024

I2I-Mamba: Multi-modal medical image synthesis via selective state space modeling
Omer F. Atli, Bilal Kabas, Fuat Arslan, Mahmut Yurt, Onat Dalmaz, Tolga Çukur
Medical Image Synthesis Multi Contrast Selective State Space Convolutional Backbone

April 17, 2024

Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding
George Retsinas, Niki Efthymiou, Petros Maragos
Point Cloud 3D Annotation Convolutional Backbone 3D Sparse Pose Code Mushroom Detection Mushroom Image Recognition

February 23, 2024

Self-Supervised Pre-Training for Table Structure Recognition Transformer
ShengYun Peng, Seongmin Lee, Xiaojing Wang, Rajarajeswari Balasubramaniyan, Duen Horng Chau
Transformer Architecture Self Supervised Pre Training Hybrid CNN Transformer Linear Transformer Table Structure Recognition Convolutional Backbone

November 9, 2023

High-Performance Transformers for Table Structure Recognition Need Early Convolutions
ShengYun Peng, Seongmin Lee, Xiaojing Wang, Rajarajeswari Balasubramaniyan, Duen Horng Chau
Hybrid CNN Transformer Table Structure Recognition Convolutional Backbone High Performance Transformer

September 19, 2023

Exploiting Causality Signals in Medical Images: A Pilot Study with Empirical Results
Gianluca Carloni, Sara Colantonio
Medical Image Empirical Study Pilot Study Convolutional Backbone Causality Extraction Prostate Magnetic Resonance Causal Influence Causality Detection Visual Causality Discovery

August 22, 2023

Coarse-to-Fine Multi-Scene Pose Regression with Transformers
Yoli Shavit, Ron Ferens, Yosi Keller
Transformer Megatron Decepticons Coarse to Fine Pose Regression Convolutional Backbone Pose Prediction Absolute Pose Multi Scene Absolute Pose Regressors

February 9, 2023

3D Human Pose and Shape Estimation via HybrIK-Transformer
Boris N. Oreshkin
3D Pose 3D Human Pose Inverse Kinematics Shape Estimation Convolutional Backbone Pose Lifting

December 22, 2022

Multi Lane Detection
Fei Wu, Luoyu Chen
Autonomous Driving Lane Detection Robust Detection Convolutional Backbone

December 20, 2022

ParallelNet: Multi-mode Trajectory Prediction by Multi-mode Trajectory Fusion
Fei Wu, Luoyu Chen, Hao Lu
Autonomous Driving Future Trajectory Convolutional Backbone Parallel Hybrid Network

December 14, 2022

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping
Zhuoqian Yang, Shikai Li, Wayne Wu, Bo Dai
Generative Adversarial Network 2 Dimensional 3D Human Camera Pose Photorealistic Image Convolutional Backbone Human Image Generation

November 20, 2022

A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective
Praveen Kumar Rajendran, Quoc-Vinh Lai-Dang, Luiz Felipe Vecchietti, Dongsoo Har
Cross Domain Convolutional Backbone Absolute Pose Absolute Pose Regression Barlow Twin Absolute Pose Regressors

November 4, 2022

RCDPT: Radar-Camera fusion Dense Prediction Transformer
Chen-Chou Lo, Patrick Vandewalle
Vision Transformer Depth Estimation Convolutional Backbone Dense Prediction Transformer

August 3, 2022

Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition
Mei Chee Leong, Haosong Zhang, Hui Li Tan, Liyuan Li, Joo Hwee Lim
Fine Grained Cross Modal Convolutional Backbone

July 14, 2022

Fine-grained Few-shot Recognition by Deep Object Parsing
Ruizhao Zhu, Pengkai Zhu, Samarth Mishra, Venkatesh Saligrama
Convolutional Backbone Shape Part Shot Support Deep Object Shot Fine Grained

April 15, 2022

Efficient Architecture Search for Diverse Tasks
Junhong Shen, Mikhail Khodak, Ameet Talwalkar
Neural Architecture Search Online autoML Architecture Search Differentiable Neural Architecture Search Diverse Task Convolutional Backbone Standard Convolutional

March 22, 2022

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers
Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu, Chiew-Lan Tai
Transformer Megatron Decepticons 3D Object Detection LiDAR Point Cloud Fusion Method LiDAR Camera Fusion Convolutional Backbone Blood Transfusion

March 8, 2022

Counting with Adaptive Auxiliary Learning
Yanda Meng, Joshua Bridge, Meng Wei, Yitian Zhao, Yihong Qiao, Xiaoyun Yang, Xiaowei Huang, Yalin Zheng
Automatic Counting Auxiliary Task Object Counting Auxiliary Learning Convolutional Backbone

January 31, 2022

Adversarial Masking for Self-Supervised Learning
Yuge Shi, N. Siddharth, Philip H. S. Torr, Adam R. Kosiorek
Self Supervised Learning Self Supervised Learning Method Image Encoder Adversarial Objective Adversarial Mask Convolutional Backbone

December 9, 2021

PE-former: Pose Estimation Transformer
Paschalis Panteleris, Antonis Argyros
Encoder Decoder Vision Transformer Architecture Convolutional Backbone Pure Transformer X Former CNN Backbone Pose Induced Video Transformer