# Image Segmentation

A PyTorch-based FPN architecture image segmentation model supporting multiple encoders, suitable for semantic segmentation tasks.

This paper proposes a method to reinterpret Vision Transformer (ViT) as an image segmentation model, demonstrating ViT's potential in image segmentation tasks.

This paper proposes a method to reinterpret Vision Transformer (ViT) as an image segmentation model, revealing ViT's potential in image segmentation tasks.

This paper proposes an image segmentation model based on Vision Transformer (ViT), revealing the potential of ViT in image segmentation tasks.

This model reveals the potential of Vision Transformer (ViT) in image segmentation tasks by adapting its architecture for segmentation purposes.

This paper proposes a method to reinterpret Vision Transformer (ViT) as an image segmentation model, demonstrating ViT's potential in image segmentation tasks.

PAN is an image segmentation model implemented in PyTorch, utilizing pyramid attention mechanisms to enhance feature extraction capabilities

A PyTorch-implemented FPN image segmentation model that supports various encoder architectures, suitable for semantic segmentation tasks.

SUM is a model for mask generation, with unspecified specific functionality, potentially involving mask generation tasks for images or text.

PyTorch-based Unet image segmentation model supporting multiple encoder architectures

A PyTorch implementation of the Unet image segmentation model, supporting various encoder architectures and pretrained weights.

SAM2-Hiera Small is a compact variant of Meta's SAM2 model for efficient mask generation tasks.

Image segmentation dataset for human parsing tasks

SlimSAM-77-Uniform is a lightweight SAM (Segment Anything Model) designed for efficient image segmentation tasks.

SlimSAM is a compressed version of the Segment Anything (SAM) model, significantly reducing parameters and computational requirements through pruning and distillation techniques while maintaining high-quality object segmentation capabilities.

An image segmentation model fine-tuned based on nvidia/mit-b5, specialized in crack detection tasks

Large-scale image segmentation model based on Vision Transformer architecture, capable of generating high-quality object masks from input points

A foundational image segmentation model based on ViT architecture, capable of generating high-quality object masks from input points