# Progressive Feature Alignment for Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/1811.08585 · HTML: https://mlsanity.com/paper/1811.08585/

## Key facts

- Cited by 183 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 30 of 183)

- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09415/) (2021)
- [Pin the Memory: Learning to Generalize Semantic Segmentation](https://mlsanity.com/paper/2204.03609/) (2022)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)
- [A Probabilistic Framework for Lifelong Test-Time Adaptation](https://mlsanity.com/paper/2212.09713/) (2022)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [Multi-Target Domain Adaptation with Collaborative Consistency Learning](https://mlsanity.com/paper/2106.03418/) (2021)
- [Compound Domain Generalization via Meta-Knowledge Encoding](https://mlsanity.com/paper/2203.13006/) (2022)
- [Cross-category Video Highlight Detection via Set-based Learning](https://mlsanity.com/paper/2108.11770/) (2021)
- [Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation](https://mlsanity.com/paper/2308.05493/) (2023)
- [Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation](https://mlsanity.com/paper/2104.00808/) (2021)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision](https://mlsanity.com/paper/2201.07929/) (2022)
- [Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation](https://mlsanity.com/paper/2403.12505/) (2024)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (2021)
- [I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors](https://mlsanity.com/paper/2103.13757/) (2021)
- [ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing](https://mlsanity.com/paper/2210.11539/) (2022)
- [360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes](https://mlsanity.com/paper/2404.16501/) (2024)
- [Domain-Specific Suppression for Adaptive Object Detection](https://mlsanity.com/paper/2105.03570/) (2021)
- [Dual Path Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2108.06337/) (2021)
- [Balancing Logit Variation for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2306.02061/) (2023)
- [AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2209.10904/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discriminative domain transfer in virtue of pseudo-labels to enforce the class-level distribution alignment across the source and target domains. These methods, however, are vulnerable to the error accumulation and thus incapable of preserving cross-domain category consistency, as the pseudo-labeling accuracy is not guaranteed explicitly. In this paper, we propose the Progressive Feature Alignment Network (PFAN) to align the discriminative features across domains progressively and effectively, via exploiting the intra-class variation in the target domain. To be specific, we first develop an Easy-to-Hard Transfer Strategy (EHTS) and an Adaptive Prototype Alignment (APA) step to train our model iteratively and alternatively. Moreover, upon observing that a good domain adaptation usually requires a non-saturated source classifier, we consider a simple yet efficient way to retard the convergence speed of the source classification loss by further involving a temperature variate into the soft-max function. The extensive experimental results reveal that the proposed PFAN exceeds the state-of-the-art performance on three UDA datasets.