Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
This addresses the problem of refining CNN models for computer vision tasks, offering an incremental improvement by enabling feedback in pre-trained networks.
The paper tackles the lack of feedback mechanisms in convolutional neural networks (CNNs) by proposing a 'Learning with Rethinking' algorithm that uses feedback layers to recurrently improve predictions, demonstrating performance boosts on benchmark datasets like CIFAR-100, CIFAR-10, MNIST-background-image, and ILSVRC-2012.
Recent years have witnessed the great success of convolutional neural network (CNN) based models in the field of computer vision. CNN is able to learn hierarchically abstracted features from images in an end-to-end training manner. However, most of the existing CNN models only learn features through a feedforward structure and no feedback information from top to bottom layers is exploited to enable the networks to refine themselves. In this paper, we propose a "Learning with Rethinking" algorithm. By adding a feedback layer and producing the emphasis vector, the model is able to recurrently boost the performance based on previous prediction. Particularly, it can be employed to boost any pre-trained models. This algorithm is tested on four object classification benchmark datasets: CIFAR-100, CIFAR-10, MNIST-background-image and ILSVRC-2012 dataset. These results have demonstrated the advantage of training CNN models with the proposed feedback mechanism.