EMN: Brain-inspired Elastic Memory Network for Quick Domain Adaptive Feature Mapping
This addresses the deployment challenge of domain adaptation on lightweight edge devices, though it is an incremental improvement over existing methods.
The paper tackles the problem of time-consuming optimization in domain adaptation by proposing a gradient-free Elastic Memory Network (EMN) that enables quick fine-tuning of feature-to-prediction mapping, achieving up to 10% performance enhancement with less than 1% timing cost compared to traditional methods.
Utilizing unlabeled data in the target domain to perform continuous optimization is critical to enhance the generalization ability of neural networks. Most domain adaptation methods focus on time-consuming optimization of deep feature extractors, which limits the deployment on lightweight edge devices. Inspired by the memory mechanism and powerful generalization ability of biological neural networks in human brains, we propose a novel gradient-free Elastic Memory Network, namely EMN, to support quick fine-tuning of the mapping between features and prediction without heavy optimization of deep features. In particular, EMN adopts randomly connected neurons to memorize the association of features and labels, where the signals in the network are propagated as impulses, and the prediction is made by associating the memories stored on neurons based on their confidence. More importantly, EMN supports reinforced memorization of feature mapping based on unlabeled data to quickly adapt to a new domain. Experiments based on four cross-domain real-world datasets show that EMN can achieve up to 10% enhancement of performance while only needing less than 1% timing cost of traditional domain adaptation methods.