11 papers with code • 0 benchmarks • 3 datasets
Inspired by the success of edge enhanced GAN (EEGAN) and ESRGAN, we apply a new edge-enhanced super-resolution GAN (EESRGAN) to improve the image quality of remote sensing images and use different detector networks in an end-to-end manner where detector loss is backpropagated into the EESRGAN to improve the detection performance.
Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations.
As it is very difficult and expensive to obtain class labels in real world, we integrate the proposed WCRN with AL to improve its generalization by using the most informative training samples.
We conduct experiments on land cover classification (BigEarthNet) and West Nile Virus detection, showing that colorization is a solid pretext task for training a feature extractor.
This paper proposes an architect-independent Consensual Collaborative Multi-Label Learning (CCML) method to train deep classifiers under input-dependent (heteroscedastic) multi-label noise in the MLC problems.