A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Specifically, our main idea is to learn the sharing pattern through a task-specific policy that selectively chooses which layers to execute for a given task in the multi-task network. ...
Unlike existing methods, we propose an adaptive sharing approach, called AdaShare, that decides what to share across which tasks to achieve the best recognition accuracy, while taking resource efficiency ...
Moreover, we will extend AdaShare for finding a fine-grained channel sharing pattern instead of layer-wise policy across tasks, for more efficient deep multi-task learning. ...
arXiv:1911.12423v2
fatcat:dlqfekp3ebe3zecsqgnddct2za
AutoMTL: A Programming Framework for Automated Multi-Task Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Multi-task learning (MTL) jointly learns a set of tasks. ...
AutoMTL takes as inputs an arbitrary backbone convolutional neural network and a set of tasks to learn, then automatically produce a multi-task model that achieves high accuracy and has small memory footprint ...
An effective approach to address the problem is multi-task learning (MTL) where a set of tasks are learned jointly to allow some parameter sharing among tasks. ...
arXiv:2110.13076v1
fatcat:riabbk35lvhdrnd2dzxd6534jq
Learning to Branch for Multi-Task Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we present an automated multi-task learning algorithm that learns where to share or branch within a network, designing an effective network topology that is directly optimized for multiple ...
Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of a network. ...
AdaShare (Sun et al., 2019) learns the sharing pattern through a task-specific policy that selectively chooses which layers to execute for a given task in a multi-task setting. ...
arXiv:2006.01895v2
fatcat:uskaljzrbfgbrhz7ryu3h6wtam
A Tree-Structured Multi-Task Model Recommender
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The major challenge is to determine where to branch out for each task given a backbone model to optimize for both task accuracy and computation efficiency. ...
Tree-structured multi-task architectures have been employed to jointly tackle multiple vision tasks in the context of multi-task learning (MTL). ...
It also promotes the leverage of multi-task learning to increase task performance and computation efficiency. ...
arXiv:2203.05092v1
fatcat:cgeitkkpnrg3nio4bcv4ujcpxq
Multi-Task Learning with Deep Neural Networks: A Survey
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. ...
In this survey, we give an overview of multi-task learning methods for deep neural networks, with the aim of summarizing both the well-established and most recent directions within the field. ...
., 2017) is one of the earliest methods for learned parameter sharing in multi-task deep learning. ...
arXiv:2009.09796v1
fatcat:d676uupucvgrbgnvsijqcexcqi
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Despite the fruitful progress, existing methods for both problems are still brittle to the same challenge -- it remains dilemmatic to integrate the common information across modalities (resp. tasks) meanwhile ...
Extensive experiments on semantic segmentation via RGB-D data and image translation through multi-domain input verify the effectiveness of our CEN compared to current state-of-the-art methods. ...
Saenko, “Adashare: Learning
what to share for efficient deep multi-task learning,” in NeurIPS,
2020. 11 ...
arXiv:2112.02252v1
fatcat:ul4gs5dajjc5lecol6psabn4pu
Measuring and Harnessing Transference in Multi-Task Learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. ...
We find these methods can lead to significant improvement over prior work on three supervised multi-task learning benchmarks and one multi-task reinforcement learning paradigm. ...
Adashare: Learning what
to share for efficient deep multi-task learning. arXiv
preprint arXiv:1911.12423, 2019.
Suteu, M. and Guo, Y. ...
arXiv:2010.15413v3
fatcat:mskg3nftpneb5lpm5o2fygumpm
Which Tasks Should Be Learned Together in Multi-task Learning?
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
when employing multi-task learning? ...
Many computer vision applications require solving multiple tasks in real-time. A neural network can be trained to solve multiple tasks simultaneously using multi-task learning. ...
Toyota Research Institute ("TRI") provided funds to assist the authors with their research but this article solely reflects the opinions and conclusions of its authors and not TRI or any other Toyota entity ...
arXiv:1905.07553v4
fatcat:mxpy5myr3nfmjd5ybdqls7bjsu
Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2112.00054v2 fatcat:ywt3v5tvc5dfpa6s2qh7lmj2p4Other Versions
Task2Sim learns this mapping by training to find the set of best parameters on a set of "seen" tasks. ...
It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance. ...
Acknowledgements We would like to thank the developers of TDW-Seth Alter, Abhishek Bhandwaldar and Jeremy Schwartz, for their assistance with the platform and its use. ...
arXiv:2112.00054v3
fatcat:rg7fihxdtrg45pnbdsdzijn7da