AIbase
EN
Home
Vit Base Patch16 224 In21k Finetuned Moderation
V

Vit Base Patch16 224 In21k Finetuned Moderation

Developed by mbehbooei
An image classification model based on Google's Vision Transformer architecture, fine-tuned specifically for content moderation tasks, achieving 90.43% accuracy on the test set
Image Classification
Transformers
Open Source License:Apache-2.0#High-precision image classification#ViT fine-tuned model#Content moderation
Downloads 752
Release Time : 9/30/2023

Model Overview

This model is an image classifier based on the Vision Transformer architecture, fine-tuned for content moderation scenarios to automatically identify inappropriate content in images.

Model Features

High accuracy
Achieves 90.43% classification accuracy on the test set
Efficient fine-tuning
Quick fine-tuning based on pre-trained models, requiring only 2 training epochs
Standardized input
Supports standard image input of 224x224 pixels

Model Capabilities

Image classification
Content moderation
Automatic image recognition

Use Cases

Content moderation
Social media content filtering
Automatically identifies and filters inappropriate image content
90.43% recognition accuracy
User-generated content moderation
Used for image moderation on UGC platforms such as forums and comment sections
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase