Transfer and Association: A Novel Detection Method for Targets without Prior Homogeneous Samples

Abstract

A primary problem faced during previous research was the gap in limited and unbalanced quantity of prior samples between computer classification tasks and targeted remote sensing applications. This paper presents the fusion method to overcome this limitation. It offers a novel method based on knowledge transfer and feature association, a strong combination of transfer learning and data fusion. The former reuses layers trained on complete data sets to compute a mid-level representation of the specific target. The latter brings additional information from heterogeneous sources to enrich the features in the target domain. Firstly, a basic convolutional neural network (B_CNN) is pretrained on to the CIFAR-10 dataset to produce a stable model responsible for general feature extraction from multiple inputs. Secondly, a transfer CNN (Trans_CNN) with fine-tuned and transferred parameters is constraint-trained to fit and switch between differing tasks. Meanwhile, the feature association (FA) frames a new feature space to achieve integration between training and testing samples from different sensors. Finally, on-line detection can be completed based on Trans_CNN to explore a state-of-the-art method to overcome the inadequate sample problems in real remote sensing applications rather than produce an unrolled version of training methods or structural improvement in CNN. Experimental results show that target detection rates without homogeneous prior samples can reach 85%. Under these conditions, the traditional CNN model is invalid.