O

Oxford Pet Segmentation

Developed by SimonLiao
A PyTorch-based FPN image segmentation model supporting various encoder architectures, suitable for semantic segmentation tasks.
Downloads 53
Release Time : 4/9/2025

Model Overview

This model is an image segmentation model based on the Feature Pyramid Network architecture, designed for semantic segmentation tasks. It supports multiple pre-trained encoders (e.g., ResNet34) and offers flexible configuration options to meet diverse needs.

Model Features

Multiple Encoder Support
Supports various pre-trained encoders (e.g., ResNet34), allowing flexible selection of backbone networks.
High Performance
Delivers excellent performance on the Oxford Pet dataset, achieving a test IoU of 0.915.
Easy to Use
Provides simple API interfaces for quick loading from pre-trained models.

Model Capabilities

Image segmentation
Semantic segmentation
Feature extraction

Use Cases

Computer Vision
Pet Image Segmentation
Used for segmenting foreground and background in pet images.
Achieved 91.5% IoU on the Oxford Pet dataset.
Medical Image Analysis
Can be used for organ or lesion segmentation in medical images.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase