Results 41 to 50 of about 83,974 (281)
Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning
, 2020 As a popular meta-learning approach, the model-agnostic meta-learning (MAML) algorithm has been widely used due to its simplicity and effectiveness. However, the convergence of the general multi-step MAML still remains unexplored. In this paper, we develop a new theoretical framework to provide such convergence guarantee for two types of objective ...
Ji, Kaiyi, Yang, Junjie, Liang, Yingbin
openaire +3 more sources
Adaptive visual detection of industrial product defects [PDF]
PeerJ Computer Science, 2023 Visual inspection of the appearance defects on industrial products has always been a research hotspot pursued by industry and academia. Due to the lack of samples in the industrial defect dataset and the serious class imbalance, deep learning technology ...
Haigang Zhang +3 more
doaj +2 more sources
Self-Supervised Deep Visual Odometry with Online Adaptation
, 2020 Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with scenes different ...
Cao, Yingdian +5 more
core +1 more source
MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction
, 2021 7 pages, 6 figures, 2 ...
Pan, Edwin, Vento, Anthony
openaire +2 more sources
Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
, 2021 We propose a new computationally-efficient first-order algorithm for Model-Agnostic Meta-Learning (MAML). The key enabling technique is to interpret MAML as a bilevel optimization (BLO) problem and leverage the sign-based SGD(signSGD) as a lower-level optimizer of BLO.
Fan, Chen, Ram, Parikshit, Liu, Sijia
openaire +2 more sources
Difficulty‑Aware Meta‑Learning for Cross‑Domain Face Forgery Detection
Nanjing Hangkong Hangtian Daxue XuebaoWith the rapid iteration of facial forgery techniques， robust detection mechanisms that can handle unseen forgery methods are increasingly crucial. However， current approaches are primarily tailored to specific forgery techniques， posing limitations in ...
JIN Shichen, TAN Xiaoyang
doaj +1 more source
Personalizing Dialogue Agents via Meta-Learning
, 2019 Existing personalized dialogue models use human designed persona descriptions to improve dialogue consistency. Collecting such descriptions from existing dialogues is expensive and requires hand-crafted feature designs.
Fung, Pascale +3 more
core +1 more source
Toward Multimodal Model-Agnostic Meta-Learning
, 2018 Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common initialization shared across the entire task distribution, substantially limiting the diversity of the task ...
Vuorio, Risto +3 more
openaire +2 more sources
Meta-Learning by the Baldwin Effect
, 2018 The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstration of its necessity in empirically challenging tasks. Here we show that
Fernando, Chrisantha Thomas +8 more
core +1 more source
CLDP-pFedAvg: Safeguarding Client Data Privacy in Personalized Federated Averaging
MathematicsThe personalized federated averaging algorithm integrates a federated averaging approach with a model-agnostic meta-learning technique. In real-world heterogeneous scenarios, it is essential to implement additional privacy protection techniques for ...
Wenquan Shen, Shuhui Wu, Yuanhong Tao
doaj +1 more source