# Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation

arXiv: https://arxiv.org/abs/2106.12123 · HTML: https://mlsanity.com/paper/2106.12123/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 23 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Domain Adaptation for Semantic Segmentation with Maximum Squares Loss](https://mlsanity.com/paper/1909.13589/) (2019)
- [Unsupervised Scene Adaptation with Memory Regularization in vivo](https://mlsanity.com/paper/1912.11164/) (2019)
- [Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations](https://mlsanity.com/paper/2011.08502/) (2020)

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization](https://mlsanity.com/paper/2212.00979/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Bidirectional Uncertainty-Based Active Learning for Open Set Annotation](https://mlsanity.com/paper/2402.15198/) (2024)
- [Pre-training Language Models with Deterministic Factual Knowledge](https://mlsanity.com/paper/2210.11165/) (2022)
- [Trust And Balance: Few Trusted Samples Pseudo-Labeling and Temperature Scaled Loss for Effective Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2409.00741/) (2024)

## Abstract (arXiv)

It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict limits: 1) access to internal specifications of source models is a must; and 2) pseudo labels should be clean during self-training, making critical tasks relying on semantic segmentation unreliable. Aiming at these pitfalls, this study develops a domain adaptive solution to semantic segmentation with pseudo label rectification (namely textitPR-SFDA), which operates in two phases: 1) textitConfidence-regularized unsupervised learning: Maximum squares loss applies to regularize the target model to ensure the confidence in prediction; and 2) textitNoise-aware pseudo label learning: Negative learning enables tolerance to noisy pseudo labels in training, meanwhile positive learning achieves fast convergence. Extensive experiments have been performed on domain adaptive semantic segmentation benchmark, textitGTA5 → Cityscapes. Overall, textitPR-SFDA achieves a performance of 49.0 mIoU, which is very close to that of the state-of-the-art counterparts. Note that the latter demand accesses to the source model's internal specifications, whereas the textitPR-SFDA solution needs none as a sharp contrast.