Advances and challenges in meta-learning: A technical review

A Vettoruzzo, MR Bouguelia… - IEEE transactions on …, 2024 - ieeexplore.ieee.org
Meta-learning empowers learning systems with the ability to acquire knowledge from
multiple tasks, enabling faster adaptation and generalization to new tasks. This review …

Meta-learning in neural networks: A survey

T Hospedales, A Antoniou, P Micaelli… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Weight-sharing neural architecture search: A battle to shrink the optimization gap

L **e, X Chen, K Bi, L Wei, Y Xu, L Wang… - ACM Computing …, 2021 - dl.acm.org
Neural architecture search (NAS) has attracted increasing attention. In recent years,
individual search methods have been replaced by weight-sharing search methods for higher …

Design space for graph neural networks

J You, Z Ying, J Leskovec - Advances in Neural Information …, 2020 - proceedings.neurips.cc
The rapid evolution of Graph Neural Networks (GNNs) has led to a growing number of new
architectures as well as novel applications. However, current research focuses on proposing …

NAS-FAS: Static-dynamic central difference network search for face anti-spoofing

Z Yu, J Wan, Y Qin, X Li, SZ Li… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Face anti-spoofing (FAS) plays a vital role in securing face recognition systems. Existing
methods heavily rely on the expert-designed networks, which may lead to a sub-optimal …

Learning to branch for multi-task learning

P Guo, CY Lee, D Ulbricht - International conference on …, 2020 - proceedings.mlr.press
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 …

Hr-nas: Searching efficient high-resolution neural architectures with lightweight transformers

M Ding, X Lian, L Yang, P Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
High-resolution representations (HR) are essential for dense prediction tasks such as
segmentation, detection, and pose estimation. Learning HR representations is typically …

Towards fast adaptation of neural architectures with meta learning

D Lian, Y Zheng, Y Xu, Y Lu, L Lin, P Zhao… - International …, 2020 - openreview.net
Recently, Neural Architecture Search (NAS) has been successfully applied to multiple
artificial intelligence areas and shows better performance compared with hand-designed …

Transnas-bench-101: Improving transferability and generalizability of cross-task neural architecture search

Y Duan, X Chen, H Xu, Z Chen… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract Recent breakthroughs of Neural Architecture Search (NAS) extend the field's
research scope towards a broader range of vision tasks and more diversified search spaces …

An evaluation of edge tpu accelerators for convolutional neural networks

K Seshadri, B Akin, J Laudon… - 2022 IEEE …, 2022 - ieeexplore.ieee.org
Edge TPUs are a domain of accelerators for low-power, edge devices and are widely used
in various Google products such as Coral and Pixel devices. In this paper, we first discuss …