Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-Multi-Task-Learning
A list of multi-task learning papers and projects.
https://github.com/SimonVandenhende/Awesome-Multi-Task-Learning
- Link
- Youtube
- Multi-Task Learning for Dense Prediction Tasks: A Survey
- [PyTorch
- An overview of multi-task learning in deep neural networks
- A survey on multi-task learning
- A comparison of loss weighting strategies for multi task learning in deep neural networks
- NYUDv2
- Cityscapes
- PASCAL
- Taskonomy
- KITTI
- SUN RGB-D
- BDD100K
- Cross-stitch networks for multi-task learning
- [PyTorch
- Nddr-cnn: Layerwise feature fusing in multi-task cnns by neural discriminative dimensionality reduction
- [Tensorflow - Task-Learning-PyTorch)]
- End-to-end multi-task learning with attention
- [PyTorch
- Integrated perception with recurrent multi-task neural networks
- Pad-net: Multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing
- Joint task-recursive learning for semantic segmentation and depth estimation
- Latent multi-task architecture learning
- Pattern-affinitive propagation across depth, surface normal and semantic segmentation
- Pattern-Structure Diffusion for Multi-Task Learning
- MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning
- [PyTorch
- Deep multi-task representation learning: A tensor factorisation approach
- Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory
- Learning multiple visual domains with residual adapters
- Learning multiple tasks with multilinear relationship networks
- Beyond shared hierarchies: Deep multitask learning through soft layer ordering
- Routing networks: Adaptive selection of non-linear functions for multi-task learning
- Piggyback: Adapting a single network to multiple tasks by learning to mask weights
- Efficient parametrization of multi-domain deep neural networks
- Attentive single-tasking of multiple tasks
- [PyTorch
- Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
- Multi-path Neural Networks for On-device Multi-domain Visual Classification
- Exploring Relational Context for Multi-Task Dense Prediction
- Universal Representation Learning from Multiple Domains for Few-shot Classification
- Learning Multiple Dense Prediction Tasks from Partially Annotated Data
- Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification
- Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels
- Feature partitioning for efficient multi-task architectures
- Learning to Branch for Multi-Task Learning
- Which Tasks Should Be Learned Together in Multi-task Learning?
- Branched multi-task networks: deciding what layers to share
- Automated Search for Resource-Efficient Branched Multi-Task Networks
- AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
- Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
- A modulation module for multi-task learning with applications in image retrieval
- Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks
- Multi-task learning as multi-objective optimization
- [PyTorch
- Adversarial multi-task learning for text classification
- Dynamic task prioritization for multitask learning
- Pareto multi-task learning
- Regularizing Deep Multi-Task Networks using Orthogonal Gradients
- Gradient surgery for multi-task learning
- [Tensorflow - Task-Learning-PyTorch)]
- Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
- Knowledge Distillation for Multi-task Learning
- [PyTorch
- InverseForm: A Loss Function for Structured Boundary-Aware Segmentation
- Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
- Large scale fine-grained categorization and domain-specific transfer learning
- Taskonomy: Disentangling task transfer learning
- [PyTorch
- Task2vec: Task embedding for meta-learning
- [PyTorch
- Representation similarity analysis for efficient task taxonomy & transfer learning
- [PyTorch
- Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
- Multitask Learning Strengthens Adversarial Robustness
- [PyTorch
- Robust Learning Through Cross-Task Consistency
- Anomaly Detection in Video via Self-Supervised and Multi-Task Learning
- Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets From 3D Scans