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.
☆250Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for pytorch-grad-norm
- Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning☆584Updated 4 years ago
- This in my Demo of Chen et al. "GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks" ICML 2018☆169Updated 3 years ago
- ☆144Updated 2 years ago
- MSc group project: Reproduction of 'Multi-Task Learning using Uncertainty to Weigh Losses for Scene Geometry and Semantics'; A. Kendall, …☆84Updated 5 years ago
- Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics☆547Updated 3 years ago
- PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).☆780Updated 2 years ago
- The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].☆675Updated 2 years ago
- Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]☆207Updated 6 months ago
- The Implementation of "Auto-Lambda: Disentangling Dynamic Task Relationships" [TMLR 2022].☆129Updated last year
- A list of multi-task learning papers and projects.☆362Updated 2 years ago
- Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"☆308Updated 3 years ago
- PyTorch implementation of the GradNorm☆72Updated 2 months ago
- Code for "Gradient Surgery for Multi-Task Learning"☆304Updated 4 years ago
- Pytorch implementation of the paper "Circle Loss: A Unified Perspective of Pair Similarity Optimization"☆456Updated 4 years ago
- A multi-task learning example for the paper https://arxiv.org/abs/1705.07115☆843Updated 4 years ago
- Source code for Neural Information Processing Systems (NeurIPS) 2018 paper "Multi-Task Learning as Multi-Objective Optimization"☆984Updated 2 months ago
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning☆111Updated 3 years ago
- Multi-head attention in PyTorch☆147Updated 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 …☆459Updated 4 months ago
- Multi-Task Learning Framework on PyTorch. State-of-the-art methods are implemented to effectively train models on multiple tasks.☆148Updated 5 years ago
- [CVPR 2022 Oral] Balanced MSE for Imbalanced Visual Regression https://arxiv.org/abs/2203.16427☆370Updated 2 years ago
- [NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation …☆560Updated 3 months ago
- PyTorch code for "Prototypical Contrastive Learning of Unsupervised Representations"☆571Updated 2 years ago
- Pytorch implementation for t-SNE with cuda to accelerate☆326Updated last year
- A collection of awesome things about mixed sample data augmentation☆132Updated 4 years ago
- A Tensorflow implementation of the paper arXiv:1604.03539☆126Updated 6 years ago
- Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML 2021) and Ranking and Tuning Pre-trained…☆203Updated last year
- [ICLR2021 Oral] Free Lunch for Few-Shot Learning: Distribution Calibration☆473Updated 3 years ago
- Awesome Multitask Learning Resources☆646Updated 3 years ago
- Official repository for CVPR21 paper "Deep Stable Learning for Out-Of-Distribution Generalization".☆184Updated 2 years ago