DILS: depth incremental learning strategy
There exist various methods for transferring knowledge between neural networks, such as parameter transfer, feature sharing, and knowledge distillation. However, these methods are typically applied when transferring knowledge between networks of equal size or from larger networks to smaller ones. Cu...
Main Authors: | Yanmei Wang, Zhi Han, Siquan Yu, Shaojie Zhang, Baichen Liu, Huijie Fan |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-01-01
|
Series: | Frontiers in Neurorobotics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2023.1337130/full |
Similar Items
-
Learning Automata Based Incremental Learning Method for Deep Neural Networks
by: Haonan Guo, et al.
Published: (2019-01-01) -
Incremental Nonlinear Dynamic Inversion Attitude Control for Helicopter with Actuator Delay and Saturation
by: Shaojie Zhang, et al.
Published: (2023-06-01) -
SIM-MultiDepth: Self-Supervised Indoor Monocular Multi-Frame Depth Estimation Based on Texture-Aware Masking
by: Xiaotong Guo, et al.
Published: (2024-06-01) -
On the Influence of the Tool Path and Intrusion Depth on the Geometrical Accuracy in Incremental Sheet Forming
by: Roman Ulrich Christopher Schmitz, et al.
Published: (2020-05-01) -
Nonconvex Nonlocal Tucker Decomposition for 3D Medical Image Super-Resolution
by: Huidi Jia, et al.
Published: (2022-04-01)