# The Hitchhiker's Guide to Prior-Shift Adaptation

arXiv: https://arxiv.org/abs/2106.11695 · HTML: https://mlsanity.com/paper/2106.11695/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Regularized Learning for Domain Adaptation under Label Shifts](https://mlsanity.com/paper/1903.09734/) (2019)
- [Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application](https://mlsanity.com/paper/1309.1541/) (2013)
- [Improving CNN classifiers by estimating test-time priors](https://mlsanity.com/paper/1805.08235/) (2018)

## Built on by (most cited first, 13 of 13)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [DocILE Benchmark for Document Information Localization and Extraction](https://mlsanity.com/paper/2302.05658/) (2023)
- [On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.03154/) (2022)
- [Improving Zero-Shot Models with Label Distribution Priors](https://mlsanity.com/paper/2212.00784/) (2022)
- [Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance](https://mlsanity.com/paper/2211.10119/) (2022)
- [Binary Quantification and Dataset Shift: An Experimental Investigation](https://mlsanity.com/paper/2310.04565/) (2023)
- [Contrastive Classification and Representation Learning with Probabilistic Interpretation](https://mlsanity.com/paper/2211.03646/) (2022)
- [GLAMI-1M: A Multilingual Image-Text Fashion Dataset](https://mlsanity.com/paper/2211.14451/) (2022)
- [The Tile: A 2D Map of Ranking Scores for Two-Class Classification](https://mlsanity.com/paper/2412.04309/) (2024)
- [Action Class Relation Detection and Classification Across Multiple Video Datasets](https://mlsanity.com/paper/2308.07558/) (2023)
- [Adapting Classifiers To Changing Class Priors During Deployment](https://mlsanity.com/paper/2309.01357/) (2023)
- [Theory-inspired Label Shift Adaptation via Aligned Distribution Mixture](https://mlsanity.com/paper/2411.02047/) (2024)
- [DirPA: Addressing Prior Shift in Imbalanced Few-shot Crop-type Classification](https://mlsanity.com/paper/2603.12905/) (2026)

## Abstract (arXiv)

In many computer vision classification tasks, class priors at test time often differ from priors on the training set. In the case of such prior shift, classifiers must be adapted correspondingly to maintain close to optimal performance. This paper analyzes methods for adaptation of probabilistic classifiers to new priors and for estimating new priors on an unlabeled test set. We propose a novel method to address a known issue of prior estimation methods based on confusion matrices, where inconsistent estimates of decision probabilities and confusion matrices lead to negative values in the estimated priors. Experiments on fine-grained image classification datasets provide insight into the best practice of prior shift estimation and classifier adaptation, and show that the proposed method achieves state-of-the-art results in prior adaptation. Applying the best practice to two tasks with naturally imbalanced priors, learning from web-crawled images and plant species classification, increased the recognition accuracy by 1.1% and 3.4% respectively.