Active Boundary Loss for Semantic Segmentation

02/04/2021
by   Chi Wang, et al.
33

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged into the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.

READ FULL TEXT

page 1

page 2

page 3

page 8

05/06/2019

SEMEDA: Enhancing Segmentation Precision with Semantic Edge Aware Loss

While nowadays deep neural networks achieve impressive performances on s...
04/16/2019

Devil is in the Edges: Learning Semantic Boundaries from Noisy Annotations

We tackle the problem of semantic boundary prediction, which aims to ide...
08/10/2019

Distance Map Loss Penalty Term for Semantic Segmentation

Convolutional neural networks for semantic segmentation suffer from low ...
03/14/2020

Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation

Automated tongue image segmentation in tongue images is a challenging ta...
02/22/2022

An Object Aware Hybrid U-Net for Breast Tumour Annotation

In the clinical settings, during digital examination of histopathologica...
04/06/2021

InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

We present a novel boundary-aware loss term for semantic segmentation us...
03/16/2022

Zero Pixel Directional Boundary by Vector Transform

Boundaries are among the primary visual cues used by human and computer ...