[1905.13539] Unsupervised Object Segmentation by Redrawing

Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks. Since the masks have to be provided at pixel level, building such a dataset for any new domain can be very costly. We present ReDO, a new model able to extract objects from images without any annotation in an unsupervised way. It relies on the idea that it should be possible to change the textures or colors of the objects without changing the overall distribution of the dataset. Following this assumption, our approach is based on an adversarial architecture where the generator is guided by an input sample: given an image, it extracts the object mask, then redraws a new object at the same location. The generator is controlled by a discriminator that ensures that the distribution of generated images is aligned to the original one. We experiment with this method on different datasets and demonstrate the goo

3 mentions: @LudovicDenoyer
Keywords: segmentation
Date: 2019/06/07 00:48

Referring Tweets

@LudovicDenoyer Can we learn to detect objects without any supervision? Yes, if we assume that an object is a part of an image that can be redrawn while keeping the image realistic. With @Mickael_Chen and Thierry Artieres - https://t.co/qa2Nao31JV https://t.co/vlI19tjGyR

Related Entries

Read more Semantic Segmentation — U-Net (Part 1) – Kerem Turgutlu – Medium
0 users, 0 mentions 2018/04/25 09:00
Read more A 2017 Guide to Semantic Segmentation with Deep Learning
20 users, 0 mentions 2018/04/22 03:40
Read more CVPR2019 survey Domain Adaptation on Semantic Segmentation
0 users, 1 mentions 2019/04/23 11:15
Read more Road detection using segmentation models and albumentations libraries on Keras
0 users, 10 mentions 2019/08/26 19:13
Read more A 2019 Guide to Semantic Segmentation - Heartbeat
0 users, 7 mentions 2019/07/29 14:24