# Resolving label uncertainty with implicit posterior models

arXiv: https://arxiv.org/abs/2202.14000 · HTML: https://mlsanity.com/paper/2202.14000/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 68 references that are in the map.
- First posted on arXiv 28 Feb 2022.

## Builds on (most cited first, 30 of 37)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [One-Shot Video Object Segmentation](https://mlsanity.com/paper/1611.05198/) (2016)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation](https://mlsanity.com/paper/1902.09513/) (2019)
- [Learning Video Object Segmentation from Static Images](https://mlsanity.com/paper/1612.02646/) (2016)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Collaborative Video Object Segmentation by Foreground-Background Integration](https://mlsanity.com/paper/2003.08333/) (2020)
- [Learning in Implicit Generative Models](https://mlsanity.com/paper/1610.03483/) (2016)
- [OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networks](https://mlsanity.com/paper/1611.01890/) (2016)
- [Tile2Vec: Unsupervised representation learning for spatially distributed data](https://mlsanity.com/paper/1805.02855/) (2018)
- [Online Adaptation of Convolutional Neural Networks for Video Object Segmentation](https://mlsanity.com/paper/1706.09364/) (2017)
- [Presence-Only Geographical Priors for Fine-Grained Image Classification](https://mlsanity.com/paper/1906.05272/) (2019)
- [Efficient Video Object Segmentation via Network Modulation](https://mlsanity.com/paper/1802.01218/) (2018)
- [Video Object Segmentation Without Temporal Information](https://mlsanity.com/paper/1709.06031/) (2017)
- [PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation](https://mlsanity.com/paper/1807.09190/) (2018)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Weakly-Supervised Neural Text Classification](https://mlsanity.com/paper/1809.01478/) (2018)
- [A Generative Appearance Model for End-to-end Video Object Segmentation](https://mlsanity.com/paper/1811.11611/) (2018)
- [Fast and Accurate Online Video Object Segmentation via Tracking Parts](https://mlsanity.com/paper/1806.02323/) (2018)
- [X-Class: Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2010.12794/) (2020)
- [Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification](https://mlsanity.com/paper/2106.06133/) (2021)

## Built on by (most cited first, 8 of 8)

- [Diffusion models as plug-and-play priors](https://mlsanity.com/paper/2206.09012/) (2022)
- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [Aligning Language Models with Human Preferences via a Bayesian Approach](https://mlsanity.com/paper/2310.05782/) (2023)
- [Using Multiple Input Modalities Can Improve Data-Efficiency and O.O.D. Generalization for ML with Satellite Imagery](https://mlsanity.com/paper/2507.13385/) (2025)
- [Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection](https://mlsanity.com/paper/2211.11534/) (2022)
- [Reflections from the Workshop on AI-Assisted Decision Making for Conservation](https://mlsanity.com/paper/2307.08774/) (2023)
- [Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation](https://mlsanity.com/paper/2308.01184/) (2023)
- [Deep autoregressive modeling for land use land cover](https://mlsanity.com/paper/2401.01395/) (2024)

## Abstract (arXiv)

We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs. This formulation unifies various machine learning settings; the weak beliefs can come in the form of noisy or incomplete labels, likelihoods given by a different prediction mechanism on auxiliary input, or common-sense priors reflecting knowledge about the structure of the problem at hand. We demonstrate the proposed algorithms on diverse problems: classification with negative training examples, learning from rankings, weakly and self-supervised aerial imagery segmentation, co-segmentation of video frames, and coarsely supervised text classification.