Learning to Segment via Cut-and-Paste

03/16/2018
by   Tal Remez, et al.
0

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

READ FULL TEXT

page 1

page 2

page 5

page 10

page 11

page 12

page 13

page 14

research
04/04/2021

Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images

Humans have a strong class-agnostic object segmentation ability and can ...
research
12/15/2022

EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation

We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste co...
research
10/11/2022

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Labeling objects with pixel-wise segmentation requires a huge amount of ...
research
05/27/2019

Unsupervised Object Segmentation by Redrawing

Object segmentation is a crucial problem that is usually solved by using...
research
07/05/2021

Are standard Object Segmentation models sufficient for Learning Affordance Segmentation?

Affordances are the possibilities of actions the environment offers to t...
research
03/15/2021

Deep Consensus Learning

Both generative learning and discriminative learning have recently witne...
research
04/04/2018

Normalized Cut Loss for Weakly-supervised CNN Segmentation

Most recent semantic segmentation methods train deep convolutional neura...

Please sign up or login with your details

Forgot password? Click here to reset