MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning

@article{Gao2020MTLNASTN,
  title={MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning},
  author={Yuan Gao and Haoping Bai and Zequn Jie and Jiayi Ma and Kui Jia and Wei Liu},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={11540-11549}
}
  • Yuan Gao, Haoping Bai, +3 authors Wei Liu
  • Published 2020
  • Computer Science, Mathematics
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL). Existing NAS methods typically define different search spaces according to different tasks. In order to adapt to different task combinations (i.e., task sets), we disentangle the GP-MTL networks into single-task backbones (optionally encode the task priors), and a hierarchical and layerwise features sharing/fusing scheme across them. This enables us to design a novel and general task… Expand
12 Citations
Multi-Task Learning with Deep Neural Networks: A Survey
  • 12
  • PDF
Attentive Feature Reuse for Multi Task Meta learning
  • PDF
Learning Versatile Neural Architectures by Propagating Network Codes
  • PDF
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
  • 8
  • PDF
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
  • 36
  • PDF
Exploiting Learnable Joint Groups for Hand Pose Estimation
  • Highly Influenced
  • PDF
Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems
  • Cong Hao, Deming Chen
  • Computer Science
  • ArXiv
  • 2021
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 80 REFERENCES
End-To-End Multi-Task Learning With Attention
  • 157
  • PDF
SNAS: Stochastic Neural Architecture Search
  • 406
  • Highly Influential
  • PDF
Efficient Forward Architecture Search
  • 18
  • PDF
Attentive Single-Tasking of Multiple Tasks
  • 34
  • PDF
Learning Multiple Tasks with Deep Relationship Networks
  • 75
  • PDF
Single Path One-Shot Neural Architecture Search with Uniform Sampling
  • 232
  • PDF
Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
  • 191
  • PDF
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search
  • 34
  • PDF
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory
  • I. Kokkinos
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 337
  • PDF
...
1
2
3
4
5
...