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
Meta-Transfer Learning through Hard Tasks
[article]
2019
arXiv
pre-print
Preserved Fulltext
In this paper, we propose a novel approach called meta-transfer learning (MTL) which learns to transfer the weights of a deep NN for few-shot learning tasks. ...
In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum that further boosts the learning efficiency of MTL. ...
Meta-transfer learning (MTL) is our meta-learning paradigm and hard task (HT) meta-batch is our training strategy. ...
arXiv:1910.03648v1
fatcat:l2z7dowb5bclzgr2a3ofk3z2za
Meta-Transfer Learning for Few-Shot Learning
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
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.
In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum for MTL. ...
In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. ...
Typically, weights are fine-tuned for each task, while we learn a meta-transfer learner through all tasks, which is different in terms of the underlying learning paradigm. ...
doi:10.1109/cvpr.2019.00049
dblp:conf/cvpr/SunLCS19
fatcat:d27j662prfglnoarnnz3c5ziy4
Meta-Transfer Learning for Few-Shot Learning
[article]
2019
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 addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum for MTL. ...
In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. ...
Typically, weights are fine-tuned for each task, while we learn a meta-transfer learner through all tasks, which is different in terms of the underlying learning paradigm. ...
arXiv:1812.02391v3
fatcat:mifgrgaqbramfmk3xshkqqlkla
Warm-starting DARTS using meta-learning
[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.
Additionally, we employ a simple meta-transfer architecture that was learned over multiple tasks. ...
In this work, we present a meta-learning framework to warm-start Differentiable architecture search (DARTS). ...
The authors propose Transferable Neural Architecture Search (T-NAS) based on MAML (Finn et al., 2017) and DARTS, where T-NAS learns a meta-architecture that can be adapted to a new task through only ...
arXiv:2205.06355v1
fatcat:7bbldurqpzfmhengh3ozr7tmrm
ETM: Effective Tuning Method based on Multi-objective and Knowledge Transfer in Image Recognition
2021
IEEE Access
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.
In addition, we improve the efficiency of the above tuning process by transferring knowledge. To do that, we can learn the meta parameters from other small-scale tasks to initialize the agent. ...
INDEX TERMS Image recognition, machine learning, deep learning, tuning, multi-objective, knowledge transfer. This work is licensed under a Creative Commons Attribution 4.0 License. ...
knowledge by the meta-learning) and TM (which does not transfer knowledge) methods on 12 target tasks (Table 7 ). ...
doi:10.1109/access.2021.3062366
fatcat:qx4wkbh6jjfzzabjxh3pycevny
Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
[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.
Recently, meta-learning methods have received much attention, which train a meta-learner on massive additional tasks to gain the knowledge to instruct the few-shot classification. ...
Inspired by this idea, we propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly, where easy tasks are preferred in the first phase, then, hard tasks are emphasized ...
To show the effectiveness of our expert training strategy, we compare it with meta-transfer learning (MTL), which propose to train meta-learner with hard tasks (HTs). ...
arXiv:2007.06240v1
fatcat:34qfap2as5bupemk6zdksje3oe
LEEP: A New Measure to Evaluate Transferability of Learned Representations
[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
Our analysis shows that LEEP can predict the performance and convergence speed of both transfer and meta-transfer learning methods, even for small or imbalanced data. ...
We introduce a new measure to evaluate the transferability of representations learned by classifiers. ...
Meta-transfer learning. Meta-transfer learning is a framework for learning to transfer from a source task to a target task (Wei et al., 2018b; Sun et al., 2019; Requeima et al., 2019) . ...
arXiv:2002.12462v2
fatcat:vl36ctimzjgjhnebt3snudvk2e
Meta-Learning in 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.
Other Versions
We first discuss definitions of meta-learning and position it with respect to related fields, such as transfer learning and hyperparameter optimization. ...
Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to improve the learning algorithm itself, given the experience of multiple ...
Addressing these issues through meta-generalizations of regularization, transfer learning, domain adaptation, and domain generalization are emerging directions [119] . ...
arXiv:2004.05439v2
fatcat:3r23tsxxkfbgzamow5miglkrye
Interventional Few-Shot 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
It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art ...
Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). ...
Broader Impact The proposed method aims to improve the Few-Shot Learning task. ...
arXiv:2009.13000v2
fatcat:atfbrjpz3zhmzj2aow7opnv3su
A Concise Review of Recent Few-shot Meta-learning Methods
[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.
We conclude this review with some vital current challenges and future prospects in few-shot meta-learning. ...
Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge. ...
The current few-shot meta-leaning methods try to solve this problem by extracting transferable or shared knowledge, e.g., a global initialization of parameters, from an auxiliary dataset through meta-training ...
arXiv:2005.10953v1
fatcat:v54jrpktazf3bfx4kqos4ls27y
GradMix: Multi-source Transfer across Domains and Tasks
2020
2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
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.
While previous works mostly focus on transfer learning from a single source, we study multi-source transfer across domains and tasks (MS-DTT), in a semi-supervised setting. ...
GradMix follows a meta-learning objective, which assigns layer-wise weights to the source gradients, such that the combined gradient follows the direction that minimize the loss for a small set of samples ...
[37] propose a meta-transfer learning method to address the few-shot learning task. Ren et al. [31] propose example reweighting in a meta-learning framework. ...
doi:10.1109/wacv45572.2020.9093343
dblp:conf/wacv/LiXWZK20
fatcat:2jlnqybw2vbq5psqhb364nfcke
GradMix: Multi-source Transfer across Domains and Tasks
[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.
While previous works mostly focus on transfer learning from a single source, we study multi-source transfer across domains and tasks (MS-DTT), in a semi-supervised setting. ...
GradMix follows a meta-learning objective, which assigns layer-wise weights to the source gradients, such that the combined gradient follows the direction that minimize the loss for a small set of samples ...
[37] propose a meta-transfer learning method to address the few-shot learning task. Ren et al. [31] propose example reweighting in a meta-learning framework. ...
arXiv:2002.03264v1
fatcat:oycbi6ubsjd4beb4gd6huqeb5u
Meta-learning for Few-shot Natural Language Processing: 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.
The goal of meta-learning is to train a model on a variety of tasks with rich annotations, such that it can solve a new task using only a few labeled samples. ...
We try to provide clearer definitions, progress summary and some common datasets of applying meta-learning to few-shot NLP. ...
Meta-learning vs. Transfer learning. ...
arXiv:2007.09604v1
fatcat:7w47wpup6fajzfeur63ybgqj6u
Multi-Pair Text Style Transfer on Unbalanced Data
[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.
In this work, we developed a task adaptive meta-learning framework that can simultaneously perform a multi-pair text-style transfer using a single model. ...
The proposed method can adaptively balance the difference of meta-knowledge across multiple tasks. ...
To achieve this, we introduce meta-learning into the style-transfer problem. Meta-learning (Schmidhuber, 1987) is a method to enable generalization ability to a model over a distribution of tasks. ...
arXiv:2106.10608v1
fatcat:gnoclrbgrnea5oss5odpaujige
A Unified Transferable Model for ML-Enhanced DBMS
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2105.02418v2 fatcat:w2huokc27vc5bjtcjcwgc45wwmOther Versions
meta knowledge across DBs. ...
Recently, the database management system (DBMS) community has witnessed the power of machine learning (ML) solutions for DBMS tasks. ...
This module learns the task-specific knowledge, which can also benefit various DBs through meta-learning. ...
arXiv:2105.02418v3
fatcat:ljb66dxlkvhdtbwnam73e5mxm4
« Previous
Showing results 1 — 15 out of 50,122 results