Self-Regulation for Semantic Segmentation

08/22/2021
by   Zhang Dong, et al.
0

In this paper, we seek reasons for the two major failure cases in Semantic Segmentation (SS): 1) missing small objects or minor object parts, and 2) mislabeling minor parts of large objects as wrong classes. We have an interesting finding that Failure-1 is due to the underuse of detailed features and Failure-2 is due to the underuse of visual contexts. To help the model learn a better trade-off, we introduce several Self-Regulation (SR) losses for training SS neural networks. By "self", we mean that the losses are from the model per se without using any additional data or supervision. By applying the SR losses, the deep layer features are regulated by the shallow ones to preserve more details; meanwhile, shallow layer classification logits are regulated by the deep ones to capture more semantics. We conduct extensive experiments on both weakly and fully supervised SS tasks, and the results show that our approach consistently surpasses the baselines. We also validate that SR losses are easy to implement in various state-of-the-art SS models, e.g., SPGNet and OCRNet, incurring little computational overhead during training and none for testing.

READ FULL TEXT

page 1

page 8

research
03/26/2018

On Regularized Losses for Weakly-supervised CNN Segmentation

Minimization of regularized losses is a principled approach to weak supe...
research
08/29/2023

3D Adversarial Augmentations for Robust Out-of-Domain Predictions

Since real-world training datasets cannot properly sample the long tail ...
research
09/15/2022

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation

Since the preparation of labeled data for training semantic segmentation...
research
08/18/2018

Concept Mask: Large-Scale Segmentation from Semantic Concepts

Existing works on semantic segmentation typically consider a small numbe...
research
08/03/2021

Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation

We focus on tackling weakly supervised semantic segmentation with scribb...
research
03/16/2023

GDDS: Pulmonary Bronchioles Segmentation with Group Deep Dense Supervision

Airway segmentation, especially bronchioles segmentation, is an importan...

Please sign up or login with your details

Forgot password? Click here to reset