# Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation

arXiv: https://arxiv.org/abs/2110.11650 · HTML: https://mlsanity.com/paper/2110.11650/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 53 references that are in the map.
- First posted on arXiv 22 Oct 2021.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](https://mlsanity.com/paper/1611.06612/) (2016)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Modeling the Background for Incremental Learning in Semantic Segmentation](https://mlsanity.com/paper/2002.00718/) (2020)
- [PLOP: Learning without Forgetting for Continual Semantic Segmentation](https://mlsanity.com/paper/2011.11390/) (2020)

## Built on by (most cited first, 15 of 15)

- [Improving Generalization in Federated Learning by Seeking Flat Minima](https://mlsanity.com/paper/2203.11834/) (2022)
- [Unmasking Anomalies in Road-Scene Segmentation](https://mlsanity.com/paper/2307.13316/) (2023)
- [APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2406.08372/) (2024)
- [Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation](https://mlsanity.com/paper/2405.08458/) (2024)
- [Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation](https://mlsanity.com/paper/2309.04573/) (2023)
- [Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey](https://mlsanity.com/paper/2303.08557/) (2023)
- [Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation](https://mlsanity.com/paper/2405.15265/) (2024)
- [Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images](https://mlsanity.com/paper/2204.07969/) (2022)
- [Hierarchical Instance Mixing across Domains in Aerial Segmentation](https://mlsanity.com/paper/2210.06216/) (2022)
- [TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentation](https://mlsanity.com/paper/2409.05393/) (2024)
- [Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2302.08785/) (2023)
- [A Survey of Deep Visual Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2303.09253/) (2023)
- [Class-Agnostic Region-of-Interest Matching in Document Images](https://mlsanity.com/paper/2506.21055/) (2025)
- [Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation](https://mlsanity.com/paper/2507.19140/) (2025)
- [Enhancing Visual Domain Adaptation with Source Preparation](https://mlsanity.com/paper/2306.10142/) (2023)

## Abstract (arXiv)

In this paper we consider the task of semantic segmentation in autonomous driving applications. Specifically, we consider the cross-domain few-shot setting where training can use only few real-world annotated images and many annotated synthetic images. In this context, aligning the domains is made more challenging by the pixel-wise class imbalance that is intrinsic in the segmentation and that leads to ignoring the underrepresented classes and overfitting the well represented ones. We address this problem with a novel framework called Pixel-By-Pixel Cross-Domain Alignment (PixDA). We propose a novel pixel-by-pixel domain adversarial loss following three criteria: (i) align the source and the target domain for each pixel, (ii) avoid negative transfer on the correctly represented pixels, and (iii) regularize the training of infrequent classes to avoid overfitting. The pixel-wise adversarial training is assisted by a novel sample selection procedure, that handles the imbalance between source and target data, and a knowledge distillation strategy, that avoids overfitting towards the few target images. We demonstrate on standard synthetic-to-real benchmarks that PixDA outperforms previous state-of-the-art methods in (1-5)-shot settings.