The Best 1347 Image Classification Tools in 2025

An NSFW image classification model based on the ViT architecture, pre-trained on ImageNet-21k via supervised learning and fine-tuned on 80,000 images to distinguish between normal and NSFW content.

An image classification model based on Vision Transformer architecture, pre-trained on the ImageNet-21k dataset, suitable for multi-category image classification tasks

A small-scale vision Transformer model trained using the DINOv2 method, extracting image features through self-supervised learning

Vision Transformer model pre-trained on ImageNet-21k and fine-tuned on ImageNet for image classification tasks

A Vision Transformer model pretrained on the ImageNet-21k dataset for image classification tasks.

Vision Transformer model trained using the DINOv2 method, extracting image features through self-supervised learning

An image classification model built with PyTorch and HuggingPics for recognizing gender in images

An image classification model based on Vision Transformer (ViT) architecture, specifically designed to detect whether images contain NSFW (Not Safe For Work) content.

The Hybrid Vision Transformer (ViT) model combines convolutional networks and Transformer architectures for image classification tasks, excelling on ImageNet.

This is an image classification model based on the PyTorch framework and generated using HuggingPics tools, specifically designed for gender classification tasks.

MobileViT is a lightweight, low-latency vision Transformer model that combines the strengths of CNNs and Transformers, making it suitable for mobile devices.

Phikon is a self-supervised learning model for histopathology based on iBOT training, primarily used for extracting features from histology image patches.

ViT-Tiny model converted from the timm repository, suitable for image classification tasks, with usage consistent with the ViT-base model

A vision Transformer model trained using the DINOv2 method, extracting robust visual features from massive image data through self-supervised learning

BEiT is a Vision Transformer (ViT)-based image classification model, pre-trained in a self-supervised manner on ImageNet-22k and fine-tuned on the same dataset.

ViT-tiny model converted from timm codebase, suitable for image classification tasks

Vision Transformer model trained with self-supervised DINOv2, specifically designed for encoding chest X-ray images

Swin Transformer v2 is a vision Transformer model that achieves efficient image classification through hierarchical feature maps and local window self-attention mechanisms.

Swin Transformer is a hierarchical vision transformer based on shifted windows, suitable for image classification tasks.

EfficientNet is a mobile-friendly pure convolutional model that achieves excellent performance in image classification tasks by uniformly scaling depth/width/resolution dimensions with compound coefficients.

ResNet-50 is a residual network model pre-trained on ImageNet-1k, using the v1.5 architecture improvement, suitable for image classification tasks.

MobileNet V2 is a lightweight convolutional neural network designed for mobile devices, achieving a balance between latency, model size, and accuracy.

BEiT is an image classification model based on Vision Transformer (ViT) architecture, pretrained with self-supervised learning on ImageNet-21k and fine-tuned on ImageNet-1k.

Prov-GigaPath is a whole-slide foundation model for digital pathology based on real-world data, designed to extract patch-level and slide-level features from pathology slides.

Large-scale image classification model based on Transformer architecture, pre-trained and fine-tuned on ImageNet-21k and ImageNet-1k datasets

An image classification model for categorizing human skin types, committed to fairness to ensure accurate performance across all skin tones.

Vision Transformer (ViT) is an image classification model based on the transformer architecture, pre-trained on ImageNet-21k and fine-tuned on ImageNet.

Lightweight NSFW image detection model with 98.56% accuracy, size only 1/18-1/20 of similar models

DeiT is a data-efficient image Transformer model trained with attention mechanisms, pretrained and fine-tuned on the ImageNet-1k dataset at 224x224 resolution.

ResNet model trained on ImageNet-1k, utilizing residual connection structure, supports image classification tasks

An image classification model based on Vision Transformer architecture, used to detect real images versus AI-generated fake images.

A Vision Transformer model trained using the DINO self-supervised method, based on the ViT architecture and pretrained on the ImageNet-1k dataset.

A Vision Transformer (ViT) image feature model with registers, pre-trained using self-supervised DINOv2 method on the LVD-142M dataset.

This Vision Transformer (ViT) model is pre-trained on the ImageNet-21k dataset and then fine-tuned on the ImageNet dataset, suitable for image classification tasks.

A vision Transformer model trained using the DINOv2 method for self-supervised image feature extraction

A Vision Transformer model trained with self-supervised DINO method using 8x8 image patches, suitable for image feature extraction tasks

Swin Transformer is a hierarchical vision Transformer that achieves linear computational complexity by computing self-attention within local windows, making it suitable for image classification tasks.

This model is an image classification model fine-tuned on the PETA dataset based on the BEiT architecture, used for recognizing pedestrian gender with an accuracy of 91.07%.

A Vision Transformer model pretrained on the ImageNet-21k dataset, suitable for image feature extraction and downstream task fine-tuning.

An image feature model based on Vision Transformer (ViT), trained using the self-supervised DINO method, suitable for image classification and feature extraction tasks.

MobileNet V2 is a lightweight vision model optimized for mobile devices, excelling in image classification tasks.

A NSFW (Not Safe For Work) content detection model fine-tuned based on Google Vision Transformer, capable of identifying 5 types of image content