Label super-resolution networks

no code implementations • ICLR 2019 • Kolya Malkin, Caleb Robinson, Le Hou, Nebojsa Jojic

We present a deep learning-based method for super-resolving coarse (low-resolution) labels assigned to groups of image pixels into pixel-level (high-resolution) labels, given the joint distribution between those low- and high-resolution labels.

Semantic Segmentation Super-Resolution

Label Super Resolution with Inter-Instance Loss

no code implementations • 9 Apr 2019 • Maozheng Zhao, Le Hou, Han Le, Dimitris Samaras, Nebojsa Jojic, Danielle Fassler, Tahsin Kurc, Rajarsi Gupta, Kolya Malkin, Shroyer Kenneth, Joel Saltz

On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient.

Segmentation Semantic Segmentation +1

Human-Machine Collaboration for Fast Land Cover Mapping

no code implementations • 10 Jun 2019 • Caleb Robinson, Anthony Ortiz, Kolya Malkin, Blake Elias, Andi Peng, Dan Morris, Bistra Dilkina, Nebojsa Jojic

This bi-directional feedback loop allows humans to learn how the model responds to new data.

Active Learning