.png){kind=icon}
.png){kind=icon}
Return
Multimodal Continual Learning Using Online Dictionary Updating
.png){kind=icon}
PRE
AI
DOI：10.1109/TCDS.2020.2973280.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article studies the continual learning task from the perspective of multimodal fusion. In the multimodal fusion problem, the unified representations of heterogeneous modalities are continuously updated, while the classifier is also constantly refreshed for each multimodal learning task. To tackle this point, we establish a continual learning framework for multimodal learning and design an effective online dictionary updating method. Finally, we experimentally verify a complex material identification task and obtain promising results.
Keywords:
Task analysis
Dictionaries
Robots
Machine learning
Encoding
Learning systems
Knowledge based systems
Continual learning
dictionary updating
multimodal fusion
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.9
Papers:
1.0K
Citations:
3.5K