Image Classification

Popular image classification model focusing on visual tasks.

Model specialized in detecting NSFW content in images.

A model specializing in detecting deep fake content.

A collection of pre-trained models for generative tasks.

Visual Transformer model optimized for image classification.

Detects not safe for work content to differentiate suitable materials.

A model for image understanding and classification.

Small Vision Transformer model for image classification.

Tiny Vision Transformer model focusing on quick inference.

CNN model enhanced for visual tasks.

Vision transformer model refined for image classification.

Large vision transformer model for efficient image classification.

Visual transformer model for predicting fan preferences.

Combines image understanding with textual information in a unified model.

Vision model built to analyze images at a high level of detail.

Small yet powerful model for image analysis.

Classic architecture adapted for image classification tasks.

Creates food-related visual content using GANs.

Generates Italian food visuals, focusing on popular dishes.

A classifier model predicting the age based on visual inputs.

Identifies beans in images through sophisticated vision techniques.

Model trained for document image classification tasks.

ResNet model known for its high performance in image classification.

Vision Transformer model adapted for CIFAR-10 classification.

Swin transformer fine-tuned for satellite image classification.

Tiny ResNet model optimized for MNIST digit classification.

Vision Transformer model focused on understanding food images.

MobileViT small model optimized for mobile platforms.

An extra-small version of MobileViT for resource-constrained devices.

Small Swin transformer model optimized for varying visual tasks.

Another tiny variant of Swin transformer for efficient processing.

Large Swin transformer model for advanced visual tasks.

Vision Transformer model trained on the Fashion MNIST dataset.

Model for diagnosing skin cancer using image data.

Model designed to evaluate dental health based on photos.

Vision Transformer model focused on analyzing spectrograms.

ResNet model designed for detecting quality drift in fashion datasets.

Vision Transformer for vehicle classification and recognition.

Classification model for identifying delivery trucks.

Model designed for classifying real estate images.

Model designed for sorting rooms in a serverless architecture.

A model focused on detecting AI-generated images.

An advanced model for classifying real estate images into 30 different classes.

Model used for classifying images related to brain tumors.

Vision Transformer model tailored for complex image tasks.

Large vision transformer variant for high-resolution image processing.

Swin-based model for detecting brain tumor-related features.

Vision Transformer optimized for recognizing face expressions.

Classifies content based on safety and appropriateness for various audiences.

Detects and flags adult content in imagery effectively.

MobileNet model optimized for image recognition on mobile devices.

Analyzes facial emotions for enhanced understanding in social contexts.

Focuses on image classification tasks comparing human versus AI outputs.