2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
| Paper ID | CI-1.6 | ||
| Paper Title | MULTI-INITIALIZATION META-LEARNING WITH DOMAIN ADAPTATION | ||
| Authors | Zhengyu Chen, Donglin Wang, Westlake University, China | ||
| Session | CI-1: Theory for Computational Imaging | ||
| Location | Gather.Town | ||
| Session Time: | Wednesday, 09 June, 15:30 - 16:15 | ||
| Presentation Time: | Wednesday, 09 June, 15:30 - 16:15 | ||
| Presentation | Poster | ||
| Topic | Computational Imaging: [IMT] Computational Imaging Methods and Models | ||
| IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
| Abstract | Recently, meta learning providing multiple initializations has drawn much attention due to its capability of handling multi-modal tasks drawn from diverse distributions. However, because of the difference of class distribution between meta-training and meta-test domain, the domain shift occurs in multi-modal meta-learning setting. To improve the performance on multi-modal tasks, we propose multi-initialization meta-learning with domain adaptation (MIML-DA) to tackle such domain shift. MIML-DA consists of a modulation network and a novel meta separation network (MSN), where the modulation network is to encode tasks into common and private modulation vectors, and then MSN uses these vectors separately to update the cross-domain meta-learner via a double-gradient descent process. In addition, the regularization using inequality measure is considered to improve the generalization ability of the meta-learner. Extensive experiments demonstrate the effectiveness of our MIML-DA method to new multi-modal tasks. | ||