Recognizing objects in natural images is an intricate problem involving multiple conflicting objectives. Deep convolutional neural networks, trained on large datasets, achieve convincing results and are currently the state-of-the-art approach for this task. However, the long time needed to train such deep networks is a major drawback. We tackled this problem by reusing a previously trained network. For this purpose, we first trained a deep convolutional network on the ILSVRC-12 dataset. We then maintained the learned convolution kernels and only retrained the classification part on different datasets. Using this approach, we achieved an accuracy of 67.68% on CIFAR-100, compared to the previous state-of-the-art result of 65.43%. Furthermore, our findings indicate that convolutional networks are able to learn generic feature extractors that can be used for different tasks.
|Title of host publication||2015 International Joint Conference on Neural Networks (IJCNN)|
|Number of pages||4|
|Publication status||Published - 28.09.2015|
|Event||International Joint Conference on Neural Networks 2015 - Killarney, Ireland|
Duration: 12.07.2015 → 17.07.2015