English

Learning to Segment via Cut-and-Paste

Computer Vision and Pattern Recognition 2018-03-20 v1

Abstract

This paper 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.

Keywords

Cite

@article{arxiv.1803.06414,
  title  = {Learning to Segment via Cut-and-Paste},
  author = {Tal Remez and Jonathan Huang and Matthew Brown},
  journal= {arXiv preprint arXiv:1803.06414},
  year   = {2018}
}
R2 v1 2026-06-23T00:55:58.884Z