Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification

We deal with the problem of information fusion driven satellite image/scene classification . We propose a generic hallucination architecture considering that all the available sensor information are present during training while some of the image modalities may be absent while testing . The proposed network is evaluated extensively on a large-scale corpus of PAN-MS image pairs (scene recognition) as well as on a benchmark hyperspectral image dataset (image classification) We find that the proposed hallucination based module indeed is capable of capturing the multi-source information, albeit the explicit absence of some . of the sensor information, and aid in improved scene characterization, and help in improved . scene characterization . We explicitly incorporate concepts of knowledge distillation for the purpose of exploring the privileged (side) information in our framework and subsequently introduce an intuitive modular training approach to our framework. The proposed Network is evaluated on a . proposed network. The proposal is evaluated . to the proposed network was evaluated extensively in a large . to a large scale corpus of . image . image pairs as well and to a benchmark image dataset as well. as well to test and identify potential targets and to identify potential potential targets for future uses of the network. It is possible to use the network as a tool that can be used in the

Links: PDF - Abstract

Code :


Keywords : image - network - proposed - information - scene -

Leave a Reply

Your email address will not be published. Required fields are marked *