EE Seminar: Learning to Segment via Cut-and-Paste
Speaker: Tal Remez
Ph.D. student under the supervision of Prof. Alex Bronstein
Wednesday, May 16th, 2018 at 15:00
Room 011, Kitot Bldg., Faculty of Engineering
Learning to Segment via Cut-and-Paste
Abstract
We presents a weakly-supervised approach to object instance segmentation. Starting with known or predicted object bounding boxes, we learn object masks by playing a game of cut-and-paste in an adversarial learning setup. A mask generator takes a detection box and Faster R-CNN features, and constructs a segmentation mask that is used to cut-and-paste the object into a new image location. The discriminator tries to distinguish between real objects, and those cut and pasted via the generator, giving a learning signal that leads to improved object masks. We verify our method experimentally using Cityscapes, COCO, and aerial image datasets, learning to segment objects without ever having seen a mask in training. Our method exceeds the performance of existing weakly supervised methods, without requiring hand-tuned segment proposals, and reaches 90% of supervised performance.
