dice-loss

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)

基于Tensorflow的常用模型，包括分类分割、新型激活、卷积模块，可在Tensorflow2.X下运行。

[CVPR 2024] Official PyTorch Code of SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects

some loss functions of image segmentation

Volumetric MRI brain tumor segmentation using autoencoder regularization

Application of U-Net in Lung Segmentation-Pytorch

Meta Transfer Learning for Few Shot Semantic Segmentation using U-Net

HistoSeg is an Encoder-Decoder DCNN which utilizes the novel Quick Attention Modules and Multi Loss function to generate segmentation masks from histopathological images with greater accuracy. This repo contains the code to Test and Train the HistoSeg

A collection of deep learning models (PyTorch implemtation)

compare the performance of cross entropy, focal loss, and dice loss in solving the problem of data imbalance

[Preprint] Official implementation of "A Multimodal Feature Distillation with CNN-Transformer Network for Brain Tumor Segmentation with Incomplete Modalities".

基于PyTorch U-Net的图像边缘分割系统，支持自定义数据集训练、推理与评估，适用于工业检测、医学影像和遥感影像边缘提取

Implementation of a compact Attention Half U-Net with Attention Gates and Squeeze-and-Excitation blocks for medical image segmentation. Features a modular PyTorch pipeline, BCE-Dice hybrid loss, mixed-precision training, cosine annealing scheduler, and reproducible evaluation tools.

Attention Gate Residual UNet for image segmentation

Focal loss, Dice loss, Tversky, contrastive losses — implemented and visually compared

U-Net based deep learning pipeline for brain tumor MRI segmentation (PyTorch): brain-only Z-score normalization, Dice+BCE loss, Dice/IoU evaluation.