Simple Does It: Weakly Supervised Instance and Semantic Segmentation

03/24/2016
by   Anna Khoreva, et al.
0

Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches 95 quality of the fully supervised model, both for semantic labelling and instance segmentation.

READ FULL TEXT

page 7

page 15

page 16

page 17

page 18

page 19

page 20

page 21

research
06/02/2022

Semantic Instance Segmentation of 3D Scenes Through Weak Bounding Box Supervision

Current 3D segmentation methods heavily rely on large-scale point-cloud ...
research
08/10/2018

Weakly- and Semi-Supervised Panoptic Segmentation

We present a weakly supervised model that jointly performs both semantic...
research
06/02/2023

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

Observing the close relationship among panoptic, semantic and instance s...
research
11/17/2018

Weakly Supervised Semantic Image Segmentation with Self-correcting Networks

Building a large image dataset with high-quality object masks for semant...
research
06/08/2021

Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation is receiving great attention due...
research
07/16/2019

Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision

Training convolutional networks for semantic segmentation with strong (p...
research
07/09/2021

Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation

In order to handle the challenges of autonomous driving, deep learning h...

Please sign up or login with your details

Forgot password? Click here to reset