Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networks
This work addresses the need for efficient adaptation methods in machine learning, particularly for resource-constrained scenarios, though it is incremental as it builds on existing adapter models.
The paper tackles the problem of adapting pre-trained deep neural networks to new domains with high computational efficiency, proposing a unidirectional thin adapter (UDTA) that reduces training time and computation while achieving comparable or improved accuracy on five fine-grained classification datasets.
In this paper, we propose a new adapter network for adapting a pre-trained deep neural network to a target domain with minimal computation. The proposed model, unidirectional thin adapter (UDTA), helps the classifier adapt to new data by providing auxiliary features that complement the backbone network. UDTA takes outputs from multiple layers of the backbone as input features but does not transmit any feature to the backbone. As a result, UDTA can learn without computing the gradient of the backbone, which saves computation for training significantly. In addition, since UDTA learns the target task without modifying the backbone, a single backbone can adapt to multiple tasks by learning only UDTAs separately. In experiments on five fine-grained classification datasets consisting of a small number of samples, UDTA significantly reduced computation and training time required for backpropagation while showing comparable or even improved accuracy compared with conventional adapter models.