Picture for Shakti N. Wadekar

Shakti N. Wadekar

The Evolution of Multimodal Model Architectures

Add code
May 28, 2024
Viaarxiv icon

OneCAD: One Classifier for All image Datasets using multimodal learning

Add code
May 11, 2023
Viaarxiv icon

MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features

Add code
Oct 06, 2022
Figure 1 for MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
Figure 2 for MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
Figure 3 for MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
Figure 4 for MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
Viaarxiv icon

Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction

Add code
May 04, 2021
Figure 1 for Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction
Figure 2 for Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction
Figure 3 for Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction
Figure 4 for Towards End-to-End Deep Learning for Autonomous Racing: On Data Collection and a Unified Architecture for Steering and Throttle Prediction
Viaarxiv icon