ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation

06/15/2020
by   Antoine Saporta, et al.
20

While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the extensive pixel-level annotations that the task requires comes at a great cost. Unsupervised domain adaptation (UDA) is one approach that tries to address these issues in order to make such systems more scalable. In particular, self-supervised learning (SSL) has recently become an effective strategy for UDA in semantic segmentation. At the core of such methods lies `pseudo-labeling', that is, the practice of assigning high-confident class predictions as pseudo-labels, subsequently used as true labels, for target data. To collect pseudo-labels, previous works often rely on the highest softmax score, which we here argue as an unfavorable confidence measurement. In this work, we propose Entropy-guided Self-supervised Learning (ESL), leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. On different UDA benchmarks, ESL consistently outperforms strong SSL baselines and achieves state-of-the-art results.

READ FULL TEXT

page 2

page 7

research
07/28/2020

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

Self-supervised learning approaches for unsupervised domain adaptation (...
research
09/10/2022

Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species

Convolutional neural networks trained using manually generated labels ar...
research
01/07/2022

Leveraging Scale-Invariance and Uncertainity with Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Scenes

This paper presents FogAdapt, a novel approach for domain adaptation of ...
research
06/20/2022

Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation

This paper proposes a novel pixel-level distribution regularization sche...
research
09/30/2019

MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling

Most of the recent Deep Semantic Segmentation algorithms suffer from lar...
research
12/06/2019

Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning

Mobile robots operating in unknown urban environments encounter a wide r...
research
08/06/2021

BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

Semantic segmentation aims to predict pixel-level labels. It has become ...

Please sign up or login with your details

Forgot password? Click here to reset