Developments in imaging technology have resulted in the extremely large datasets, however, learning any useful information from these datasets, particularly using modern deep learning architectures, require large amount of annotations. Although initiatives such as ImageNet challenge and those related to Autonomous Vehicles provide such annotated data, however they are only limited to street level imagery. In many areas, such as remote sensing, there is a dearth of annotated datasets.Thus, there is a dire need of a method that allows unsupervised learning of features that are distinctive, posses reconstruction capability and are effectively compact.
Title: Dimensionality Reduction Using Discriminative Autoencoders for Remote Sensing Image Retrieval
ICIAP 2019 is the 20th edition of a series of conferences organized biennially by the Italian Member Society (CVPL, ex GIRPR) of the International Association for Pattern Recognition (IAPR).
Advancements in deep learning techniques caused a paradigm shift in feature extraction for image perception from handcrafted methods to deep methods. However, these deep features if learned through unsupervised methods bear large memory footprints and are prone to the curse of dimensionality. Traditional feature reduction schemes involving aggregation of these learned visual descriptors may lead to loss of essential information necessary for their obvious discrimination. Therefore, this research studies various feature reduction techniques for remote sensing image features. We also propose an off-the-shelf deep discriminative network with dimensionality reduction (DAE-DR), exploiting stacked autoencoder based solution to abbreviate unsupervised features without significantly affecting their discriminative and regenerative characteristics. It is observed that the spatial dimensions encoded in the feature vector are more important than increasing the number of network filters for efficient image reconstruction. Validation of our approach has been tested for remote sensing image retrieval problem. Results demonstrate that our proposed network achieves 25 times reduction in feature size with only 0.8 times depletion of retrieval score.