• Home
  • Search
  • Revisiting Domain-Adaptive Semantic Segmentation via Knowledge Distillation.
  • Cite Icon5
  • https://doi.org/10.1109/tip.2024.3501076Copy DOI Icon

Revisiting Domain-Adaptive Semantic Segmentation via Knowledge Distillation.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Numerous methods for unsupervised domain adaptation (UDA) have been proposed in semantic segmentation, achieving remarkable improvements. These methods are categorized into an adversarial learning-based approach that utilizes an additional discriminator and image translation model, and a self-supervised approach that uses a teacher model to generate pseudo labels. Among them, the self-supervised UDA approaches based on a self-training show excellent adaptability in semantic segmentation. However, erroneous estimates of the pseudo ground truths (PGTs) used in the self-training may often lead to inaccurate updates in the teacher model. Although several attempts have been made to address this issue, the teacher model updated through exponential moving average (EMA) still has a risk of propagating inaccuracies from the PGTs. Inspired by the fact that UDA shares similar principles with knowledge distillation (KD), we revisit the self-training based UDA approach from the perspective of KD and propose a novel UDA approach that employs two different teacher models. Specifically, we utilize both an EMA-updated teacher model to generate PGTs and a frozen teacher model pretrained with source data to transfer knowledge on a feature space. Since the frozen teacher model has no constraint on the model architecture unlike the EMA updated teacher model, we can effectively leverage a better representation power from the larger frozen teacher. Extensive experiments on various backbones (DeepLab-V2 [40] and DAFormer [73]) and scenarios (GTA5 → Cityscapes and SYNTHIA → Cityscapes) show that the proposed method improves segmentation performance in the target domain with its scalability. In particular, our method achieves comparable or better performance than state-of-the-arts even with a lightweight backbone.

Similar Papers
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations24

Semi-supervised domain adaptation for segmentation models on different monitoring settings

  • May 01, 2023
  • Automation in Construction
  • Yeji Hong +4
  • Conference Article
  • Citations24

Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation

  • Jul 01, 2020
  • Espace ÉTS (ETS)
  • Le Thanh Nguyen-Meidine +4
  • Conference Article

Minimizing Outputs’ Differences of Classifiers with Different Responsibilities for Unsupervised Adversarial Domain Adaptation

  • Apr 09, 2021
  • Weiran Zhang +2
  • Conference Article
  • Citations6

A simple approach for unsupervised domain adaptation

  • Dec 01, 2016
  • Xifeng Guo +2
  • Conference Article
  • Citations61

Unsupervised Domain Adaptation to Improve Image Segmentation Quality Both in the Source and Target Domain

  • Jun 01, 2019
  • Jan-Aike Bolte +7
  • PDF
  • Research Article
  • Citations221

PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network at Unpaired Cross-Modality Cardiac Segmentation

  • Jan 01, 2019
  • IEEE Access
  • Qi Dou +6
  • Conference Article
  • Citations80

Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation

  • Jan 01, 2021
  • L.T Nguyen-Meidine +5
  • Research Article
  • Citations49

IF-EDAAN: An information fusion-enhanced domain adaptation attention network for unsupervised transfer fault diagnosis

  • Feb 01, 2025
  • Mechanical Systems and Signal Processing
  • Cuiying Lin +8
  • Research Article
  • Citations15

Feature Re-Representation and Reliable Pseudo Label Retraining for Cross-Domain Semantic Segmentation.

  • Mar 01, 2024
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jing Li +5
  • Conference Article
  • Citations94

Multi-Target Domain Adaptation with Collaborative Consistency Learning

  • Jun 01, 2021
  • Takashi Isobe +7
  • Research Article
  • Citations30

Unsupervised adversarial domain adaptation with similarity diffusion for person re-identification

  • Dec 16, 2020
  • Neurocomputing
  • Geyu Tang +3
  • Conference Article
  • Citations37

Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations

  • Jan 01, 2022
  • Marvin Klingner +3
  • Conference Article
  • Citations8

Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification

  • Aug 30, 2021
  • Dongchao Yang +2
  • Research Article
  • Citations2

Optimal transport-based domain adaptation for semantic segmentation of remote sensing images

  • Jan 16, 2024
  • International Journal of Remote Sensing
  • Ziyang Shen +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.