SNN: Stacked Neural Networks
This work addresses the problem of enhancing feature quality for transfer learning in vision tasks, offering incremental improvements in accuracy and generalizability.
The paper tackled improving transfer learning by generating better features from multiple pre-trained neural networks, resulting in up to 8% accuracy improvements over state-of-the-art methods using a single network.
It has been proven that transfer learning provides an easy way to achieve state-of-the-art accuracies on several vision tasks by training a simple classifier on top of features obtained from pre-trained neural networks. The goal of this work is to generate better features for transfer learning from multiple publicly available pre-trained neural networks. To this end, we propose a novel architecture called Stacked Neural Networks which leverages the fast training time of transfer learning while simultaneously being much more accurate. We show that using a stacked NN architecture can result in up to 8% improvements in accuracy over state-of-the-art techniques using only one pre-trained network for transfer learning. A second aim of this work is to make network fine- tuning retain the generalizability of the base network to unseen tasks. To this end, we propose a new technique called "joint fine-tuning" that is able to give accuracies comparable to finetuning the same network individually over two datasets. We also show that a jointly finetuned network generalizes better to unseen tasks when compared to a network finetuned over a single task.