• DOI:10.1109/cvpr42600.2020.01360
Corpus ID: 214667523

iTAML: An Incremental Task-Agnostic Meta-learning Approach

@article{Rajasegaran2020iTAMLAI,
  title={iTAML: An Incremental Task-Agnostic Meta-learning Approach},
  author={Jathushan Rajasegaran and Salman Khan and Munawar Hayat and F. Khan and M. Shah},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={13585-13594}
}

• Jathushan Rajasegaran, Salman Khan, +2 authors M. Shah
• Published 2020
• Computer Science, Mathematics
• 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta… Expand

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed