SASFormer: Transformers for Sparsely Annotated Semantic Segmentation

12/05/2022
by   Hui Su, et al.
0

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a multi-stage training strategy. In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance. Specifically, the framework first generates hierarchical patch attention maps, which are then multiplied by the network predictions to produce correlated regions separated by valid labels. Besides, we also introduce the affinity loss to ensure consistency between the features of correlation results and network predictions. Extensive experiments showcase that our proposed approach is superior to existing methods and achieves cutting-edge performance. The source code is available at <https://github.com/su-hui-zz/SASFormer>.

READ FULL TEXT

page 1

page 3

page 4

page 5

research
03/05/2022

Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers

Weakly-supervised semantic segmentation (WSSS) with image-level labels i...
research
10/04/2022

Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation

In this work we address multi-target domain adaptation (MTDA) in semanti...
research
03/21/2022

Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation

Sparsely annotated semantic segmentation (SASS) aims to train a segmenta...
research
03/06/2022

Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) based on image-level labe...
research
02/17/2023

Model Doctor for Diagnosing and Treating Segmentation Error

Despite the remarkable progress in semantic segmentation tasks with the ...
research
03/02/2021

HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline

Deep learning-based coastline detection algorithms have begun to outshin...
research
06/23/2020

Calibrated Adversarial Refinement for Multimodal Semantic Segmentation

Ambiguities in images or unsystematic annotation can lead to multiple va...

Please sign up or login with your details

Forgot password? Click here to reset