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

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

PyTorch extensions for fast R&D prototyping and Kaggle farming

VarifocalNet: An IoU-aware Dense Object Detector

PyTorch Implementation of Focal Loss and Lovasz-Softmax Loss

An implementation of the focal loss to be used with LightGBM for binary and multi-class classification problems

[CVPR 2022] Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

Voice Activity Detection (VAD) using deep learning.

中国法研杯CAIL2019要素抽取任务第三名方案分享

Easy to use class balanced cross entropy and focal loss implementation for Pytorch

基于tf.keras的多标签多分类模型

A PyTorch implementation of U-Net for aerial imagery semantic segmentation.

Multi-class classification with focal loss for imbalanced datasets

Polyloss Pytorch Implementation

Object detection and localization with Tensorflow 2 and Keras

Custom Loss Functions and Evaluation Metrics for XGBoost and LightGBM

Catalyst.Classification

Road crack segmentation with UNet in PyTorch — Includes implementations of multiple loss functions such as Focal, Dice, and Dice + CE.

D3M - Dynamic Data Discrepancy Mitigation for Anti-spoofing - Implementation of work Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection

A sample code for Lightweight Face Recognition competition ICCV2019

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

Focal CTC for End-To-End OMR task with Class Imbalance, SangCTC (Part I)

LightGBM for handling label-imbalanced data with focal and weighted loss functions in binary and multiclass classification

[WACV'25] Official implementation of "PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplane MRI Slices".

此一project是由清华大学医学院的姚非凡与郑家瀚共同开发完成，这里运用了三个目标检测模型，来找到图像里的人脸，以及他们是否有带口罩，是个目标检测+2分类问题。 这一readme.md文件是为了帮助使用者如何正确使用我们的code。我们使用FasterRCNN可达到0.7的mAP[.5:.95]。

Implementation of RetinaNet (focal loss) by TensorFlow (object detection)

Pytorch code of Sequential/Hierarchical ERFNet with PSPNet for real-time semantic segmentation

Code for the ACL 2019 paper "Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes"

YOLO Series

An image segmentation project using PyTorch to segment the Left Atrium in 3D Late gadolinium enhanced - cardiac MR images of the human heart.