vit-base-highways-2 Open-source Vision Model - Achieves 70% Accuracy on Unknown Datasets after Fine-tuning

Vit Base Highways 2

Developed by ogimgio

A fine-tuned Vision Transformer model based on google/vit-base-patch16-224-in21k, achieving 70% accuracy on an unknown dataset

Downloads 14

Release Time : 11/19/2022

Model Overview

This is an image classification model based on the Vision Transformer architecture, fine-tuned for specific domain image recognition tasks

Efficient Image Recognition

Based on Transformer architecture, effectively captures global image features

Transfer Learning Optimization

Fine-tuned on ImageNet-21k pre-trained model to adapt to specific tasks

Medium-scale Model

ViT-base architecture balances performance and computational resource requirements

Image Classification

Feature Extraction

Transfer Learning

Computer Vision

General Image Classification

Classify and recognize input images

Achieves 70% accuracy on the evaluation set

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.018	4.17	100	1.2669	0.7
0.0326	8.33	200	1.5075	0.7

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base