Transfer Learning Using Classification Layer Features of CNN
This work addresses computational efficiency in transfer learning for practitioners, though it appears incremental as it builds on existing CNN architectures.
The paper tackles the problem of high computational cost in fine-tuning pre-trained CNNs for transfer learning by proposing a method that appends a new layer after the classification layer, resulting in faster convergence and improved average classification accuracy compared to baselines.
Although CNNs have gained the ability to transfer learned knowledge from source task to target task by virtue of large annotated datasets but consume huge processing time to fine-tune without GPU. In this paper, we propose a new computationally efficient transfer learning approach using classification layer features of pre-trained CNNs by appending layer after existing classification layer. We demonstrate that fine-tuning of the appended layer with existing classification layer for new task converges much faster than baseline and in average outperforms baseline classification accuracy. Furthermore, we execute thorough experiments to examine the influence of quantity, similarity, and dissimilarity of training sets in our classification outcomes to demonstrate transferability of classification layer features.