A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains

by   Lyndon Chan, et al.

Recently proposed methods for weakly-supervised semantic segmentation have achieved impressive performance in predicting pixel classes despite being trained with only image labels which lack positional information. Because image annotations are cheaper and quicker to generate, weak supervision is more feasible for training segmentation algorithms in certain datasets. These methods have been predominantly developed on natural scene images and it is unclear whether they can be simply transferred to other domains with different characteristics, such as histopathology and satellite images, and still perform well. Little work has been conducted in the literature on applying weakly-supervised methods to these other image domains; it is unknown how to determine whether certain methods are more suitable for certain datasets, and how to determine the best method to use for a new dataset. This paper evaluates state-of-the-art weakly-supervised semantic segmentation methods on natural scene, histopathology, and satellite image datasets. We also analyze the compatibility of the methods for each dataset and present some principles for applying weakly-supervised semantic segmentation on an unseen image dataset.


page 4

page 6

page 11

page 12

page 13

page 14

page 15

page 16


Convolutional Simplex Projection Network (CSPN) for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation has been a subject of increased ...

The effect of scene context on weakly supervised semantic segmentation

Image semantic segmentation is parsing image into several partitions in ...

Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation

Weakly-supervised semantic segmentation aims to assign each pixel a sema...

An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems

The Segment Anything Model (SAM) has demonstrated exceptional performanc...

A Centroid Loss for Weakly Supervised Semantic Segmentation in Quality Control and Inspection Application

Process automation has enabled a level of accuracy and productivity that...

Tackling the Problem of Limited Data and Annotations in Semantic Segmentation

In this work, the case of semantic segmentation on a small image dataset...

Please sign up or login with your details

Forgot password? Click here to reset