Feature Mining: A Novel Training Strategy for Convolutional Neural Network
This addresses a specific bottleneck in CNN training for improving feature representation, but it appears incremental as it builds on existing architectures without introducing a new paradigm.
The paper tackles the problem of convolutional neural networks losing local feature information during feedforward propagation by proposing Feature Mining, a parameter-free training strategy that divides features into complementary parts and reuses them, resulting in enhanced learning of local features with wide applicability across CNN models.
In this paper, we propose a novel training strategy for convolutional neural network(CNN) named Feature Mining, that aims to strengthen the network's learning of the local feature. Through experiments, we find that semantic contained in different parts of the feature is different, while the network will inevitably lose the local information during feedforward propagation. In order to enhance the learning of local feature, Feature Mining divides the complete feature into two complementary parts and reuse these divided feature to make the network learn more local information, we call the two steps as feature segmentation and feature reusing. Feature Mining is a parameter-free method and has plug-and-play nature, and can be applied to any CNN models. Extensive experiments demonstrate the wide applicability, versatility, and compatibility of our method.