Embedded Files
1) Dataset:
NYUD-v2: Segmentation, Depth
PASCAL: Segmentation, Depth, Human Parts, Normals, Saliency, Edges
2) Papers:
Paper List:
Survey
Multi-Task Learning for Dense Prediction Tasks: A Survey_tPAMI_2021 [Link] [Personal Summary]
An overview of multi-task learning in deep neural networks_arXiv_2017 [Link]
A survey on multi-task learning_ArXiv_2017 [Link]
A comparison of loss weighting strategies for multi task learning in deep neural networks_IEEE_Access_2019 [Link]
Multi-label Classification:
Deep Learning for Multi-label Classification_2014 [Link]
"Multi-label Classification via Adaptive Resonance Theory-based Clustering"
Multi-task Learning:
End-to-End Multi-Task Learning with Attention_CVPR_2019 [Paper] [Code] [Personal Summary]
Gradient Surgery for Multi-Task Learning [Paper] [Video] [Personal Summary]
A. Kendall, Y. Gal, and R. Cipolla, "Multi-Task Learning Using Uncertainty to Weigh Losses or Scene Geometry and Semantics", in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482-7491, CVPR, 2018 [Code] [Personal Summary]
Multi-Domain Multi-Task Rehearsal for Lifelong Learning_AAAI_2020 [Paper]
Multi-task Learning by Leveraging the Semantic Information_AAAI_2020 [Paper]
One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation_MICCAI_2018_TIP_2020 [Paper] [Code]
Multi-task Detect/ Segment/ Classify:
X. Dong. C. J. Taylor, and T. F. Cootes, "Defect Classification and Detection Using a Multitask Deep One-Class CNN", in IEEE Transactions on Automation Science and Engineering, 2021.
T. L. T. Le, N. Thome, S. Bernard, V. Bismuth, F. Patoureaux, "Multitask Classification and Segmentation for Cancer Diagnosis in Mammography", in International Conference on Medical Imaging with Deep Learning, MIDL, 2019.
Z. Kong, M. He, Q. Luo, X. Huang, P. Wei, Y. Cheng, L. Chen, Y. Liang, Y. Lu, X. Li, and J.Chen, "Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics", in Frontiers in Molecular Biosciences, FMOLB, 2021.
H. H. Nguyen, F. Fang; J. Yamagishi, and I. Echizen, "Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos", in IEEE 10th International Conference on Biometrics Theory, Applications and Systems, BTAS, 2019.
M. V. S. d. Cea, K. Diedrich, R. Bakalo, L. Ness and D. Richmond, "Multi-task Learning for Detection and Classification of Cancer in Screening Mammography", in Medical Image Computing and Computer Assisted Intervention, MICCAI 2020.
Joint Disaster Classification and Victim Detection using Multi-Task Learning
Evaluation of multi-task learning in deep learning-based positioning classification of mandibular third molars
T. Mordan, N. Thome, G. Henaff, M. Cord, "Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection", Advances in Neural Information Processing Systems 31, NeurIPS, 2018.
J. B. Haurum, M. Madadi, S. Escalera, T. B. Moeslund, "Multi-Task Classification of Sewer Pipe Defects and Properties Using a Cross-Task Graph Neural Network Decoder", in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV, pp. 2806-2817, 2022.
D. Wu, M. Liao, W. Zhang, and X. Wang, "YOLOP: You Only Look Once for Panoptic Driving Perception", in arXiv:2108.11250, 2022. [Code]
Reading List:
Task Relationships:
Which Tasks Should Be Learned Together in Multi-task Learning?
For transfer learning:
For NLP:
For Cross-Task Consistency:
Multi-task Loss Weighting:
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks (adjusts the weights of the losses in a way that balances the gradient magnitudes).
To align gradients:
Based on uncertainty:
To balance gradient influence:
Comparison of loss weighting strategies:
Architecture approach to MTL:
Soft-parameter sharing:
Cross-stitch Network for Multi-task Learning_CVPR_2016 [Paper]
SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems [Paper]
Self-Supervised Multi-task:
Deep Asymmetric Multi-task Feature Learning
Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing ang Back
To-do List:
You Only Learn One Representation: Unified Network for Multiple Tasks
An Overview of Multi-Task Learning in Deep Neural Networks_2017
MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning_ECCV_2020
UP-DETR: Unsupervised Pre-training for Object Detection with Transformers_CVPR_2021
Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection_2018
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN_ECCV_2018
Auxiliary Tasks in Multi-task Learning_2018
SNR: Sub-Network Routing for Flexible Parameter Sharing in Multi-task Learning
Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts [Paper] [Video]
Unfilter:
Multitask learning improves prediction of cancer drug sensitivity [Paper]
AAAI 2020:
RevMan: Revenue-Aware Multi-Task Online Insurance Recommendation
Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis
Towards Fully End-to-End Task-Oriented Dialog System with GPT-2
Deep Multi-Task Learning for Diabetic Retinopathy Grading in Fundus Images
Bridging Towers of Multi-Task Learning with a Gating Mechanism for Aspect-Based Sentiment Analysis and Sequential Metaphor Identification
Multi-Task Recurrent Modular Networks
Progressive Multi-Task Learning with Controlled information Flow for Joint Entity and Relation Extraction
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
Community-Aware Multi-Task Transportation Demand Prediction
7857: A Unified Multi-Task Learning Framework for Joint Extraction of Entities and Relations
8202: Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
Boosting Multi-task Learning through Combination of Task Labels - with Applications in ECG Phenotyping
Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-Based Recommendation
9720: Clinical Risk Prediction with Temporal Probabilistic Asymmetric Multi-Task Learning
9905: TempLe: Learning Template of Transitions for Sample Efficient Multi-Task RL
MTAAL: Multi-Task Adversarial Active Learning for Medical Named Entity Recognition and Normalization
10119: Maximum Roaming Multi-Task Learning
Page updated
Google Sites
Report abuse