ranandalon / mtl
Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
☆551Updated 3 years ago
Alternatives and similar repositories for mtl:
Users that are interested in mtl are comparing it to the libraries listed below
- A multi-task learning example for the paper https://arxiv.org/abs/1705.07115☆854Updated 4 years ago
- The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].☆691Updated 3 years ago
- ☆145Updated 3 years ago
- Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning☆608Updated 4 years ago
- PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).☆800Updated 3 years ago
- This in my Demo of Chen et al. "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks" ICML 2018☆173Updated 3 years ago
- A list of multi-task learning papers and projects.☆370Updated 3 years ago
- Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning a…☆261Updated 2 years ago
- A PyTorch Implementation of Focal Loss.☆979Updated 5 years ago
- PyTorch Implementation of Focal Loss and Lovasz-Softmax Loss☆333Updated 3 years ago
- Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"☆792Updated last year
- Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"☆1,020Updated 6 months ago
- Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019☆609Updated 3 years ago
- This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 202…☆962Updated 3 years ago
- Exploring Self-attention for Image Recognition, CVPR2020.☆752Updated 4 years ago
- The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition☆666Updated 2 years ago
- Gradually-Warmup Learning Rate Scheduler for PyTorch☆988Updated 5 months ago
- Code for "Gradient Surgery for Multi-Task Learning"☆315Updated 4 years ago
- Implementation of the mixup training method☆466Updated 6 years ago
- lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch☆334Updated 5 years ago
- [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation …☆565Updated 7 months ago
- A Tensorflow implementation of the paper arXiv:1604.03539☆128Updated 6 years ago
- The implementation of “Gradient Harmonized Single-stage Detector” published on AAAI 2019.☆620Updated 5 years ago
- Unsupervised Feature Learning via Non-parametric Instance Discrimination☆750Updated 4 years ago
- mixup: Beyond Empirical Risk Minimization☆1,178Updated 3 years ago
- Awesome Multitask Learning Resources☆659Updated 3 years ago
- [arXiv 2019] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis☆1,320Updated 4 years ago
- The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks☆337Updated 6 years ago
- Multi-Task Learning Framework on PyTorch. State-of-the-art methods are implemented to effectively train models on multiple tasks.☆149Updated 5 years ago
- 全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data …☆474Updated 9 months ago