🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

[ICML 2022] "ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning"

Robust Contrastive Learning Using Negative Samples with Diminished Semantics (NeurIPS 2021)

Code and data of the EMNLP 2022 Main Conference paper "Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives".

Detection algorithms and applications from famous papers; simple theory; solid code.

Official code for TNNLS paper "Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning"

https://teacher.bupt.edu.cn/zhuchuang/en/index.htm

Train a SVM and for detecting human upper bodies in TV series The Big Bang Theory

SuperGlue training pipeline written using Pytorch Lightning

ViIR: The Unified Framework for Fine-tuning Vietnamese Information Retrieval Models with Various Tuning Statergies.

Custom Object Detector

Implements relation extraction for biomedical texts using Hard Negative Mining to improve accuracy in identifying complex entity relationships. Includes code for data processing, training, and evaluation with BioC-format datasets.

Spring 2022 Bioimage Informatics (Self-Study ) project using triplet loss and hard negative mining

This repository stores work for a seminar for my master's degree. The course is held from the chair Intelligent Embedded Systems (IES). My topic is Approaches for finding sample pairs in contrastive learning.

This repository offers a robust implementation of biomedical relation extraction models, featuring Hard Negative Mining to boost performance. Explore baseline and HNM-enhanced models with complete code, pretrained models, and sample data for your experiments. 🦠📦