Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation

08/03/2021
by   Xiangrong Zhang, et al.
3

Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS), including single- and multi-stage process, has attracted large attention due to data labeling efficiency. In this paper, we propose to embed affinity learning of multi-stage approaches in a single-stage model. To be specific, we introduce an adaptive affinity loss to thoroughly learn the local pairwise affinity. As such, a deep neural network is used to deliver comprehensive semantic information in the training phase, whilst improving the performance of the final prediction module. On the other hand, considering the existence of errors in the pseudo labels, we propose a novel label reassign loss to mitigate over-fitting. Extensive experiments are conducted on the PASCAL VOC 2012 dataset to evaluate the effectiveness of our proposed approach that outperforms other standard single-stage methods and achieves comparable performance against several multi-stage methods.

READ FULL TEXT

page 2

page 4

page 6

page 7

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
02/19/2020

Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning

Weakly-supervised semantic segmentation is a challenging task as no pixe...
research
05/04/2023

Mitigating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation

A surge of interest has emerged in weakly supervised semantic segmentati...
research
03/07/2021

Use square root affinity to regress labels in semantic segmentation

Semantic segmentation is a basic but non-trivial task in computer vision...
research
06/07/2021

HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation

Superpixels serve as a powerful preprocessing tool in many computer visi...
research
05/16/2020

Single-Stage Semantic Segmentation from Image Labels

Recent years have seen a rapid growth in new approaches improving the ac...
research
12/07/2022

AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation

The weakly supervised instance segmentation is a challenging task. The e...

Please sign up or login with your details

Forgot password? Click here to reset