brianlan / pytorch-grad-norm
Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning adjustable weight coefficients.
☆259Updated 2 years ago
Alternatives and similar repositories for pytorch-grad-norm:
Users that are interested in pytorch-grad-norm are comparing it to the libraries listed below
- Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning☆593Updated 4 years ago
- This in my Demo of Chen et al. "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks" ICML 2018☆171Updated 3 years ago
- Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]☆209Updated 8 months ago
- Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics☆550Updated 3 years ago
- PyTorch implementation of the GradNorm☆81Updated 4 months ago
- PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).☆789Updated 3 years ago
- Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"☆311Updated 3 years ago
- ☆145Updated 3 years ago
- The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].☆683Updated 2 years ago
- MSc group project: Reproduction of 'Multi-Task Learning using Uncertainty to Weigh Losses for Scene Geometry and Semantics'; A. Kendall, …☆86Updated 5 years ago
- Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"☆998Updated 4 months ago
- The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].☆132Updated last year
- [CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427☆377Updated 2 years ago
- A list of multi-task learning papers and projects.☆369Updated 2 years ago
- Pytorch implementation for t-SNE with cuda to accelerate☆328Updated last year
- Pytorch implementation of the paper "Circle Loss: A Unified Perspective of Pair Similarity Optimization"☆458Updated 4 years ago
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning☆113Updated 4 years ago
- Code for "Gradient Surgery for Multi-Task Learning"☆309Updated 4 years ago
- PseudoLabel 2013, VAT, PI model, Tempens, MeanTeacher, ICT, MixMatch, FixMatch☆446Updated last year
- [NeurIPS 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss☆653Updated 3 years ago
- [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation …☆562Updated 5 months ago
- A multi-task learning example for the paper https://arxiv.org/abs/1705.07115☆852Updated 4 years ago
- Official repository for CVPR21 paper "Deep Stable Learning for Out-Of-Distribution Generalization".☆187Updated 2 years ago
- PyTorch code for "Prototypical Contrastive Learning of Unsupervised Representations"☆576Updated 2 years ago
- Implement the Pareto Optimizer and pcgrad to make a self-adaptive loss for multi-task☆45Updated 3 years ago
- This is a repository for Multi-task learning with toy data in Pytorch and Tensorflow☆136Updated 6 years ago
- 这里是改进了pytorch的DataParallel, 用来平衡第一个GPU的显存使用量☆230Updated 4 years ago
- Approximating Wasserstein distances with PyTorch☆458Updated last year
- This repository contains code for the paper "Decoupling Representation and Classifier for Long-Tailed Recognition", published at ICLR 202…☆954Updated 3 years ago
- An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.☆585Updated 3 years ago