# Masksembles for Uncertainty Estimation

arXiv: https://arxiv.org/abs/2012.08334 · HTML: https://mlsanity.com/paper/2012.08334/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 30 of 88)

- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [Anti-Exploration by Random Network Distillation](https://mlsanity.com/paper/2301.13616/) (2023)
- [Packed-Ensembles for Efficient Uncertainty Estimation](https://mlsanity.com/paper/2210.09184/) (2022)
- [PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness](https://mlsanity.com/paper/2312.02158/) (2023)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [Quantification of Uncertainty with Adversarial Models](https://mlsanity.com/paper/2307.03217/) (2023)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation](https://mlsanity.com/paper/2206.00050/) (2022)
- [LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks](https://mlsanity.com/paper/2405.14438/) (2024)
- [Low-field magnetic resonance image enhancement via stochastic image quality transfer](https://mlsanity.com/paper/2304.13385/) (2023)
- [ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference](https://mlsanity.com/paper/2211.11435/) (2022)
- [Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models](https://mlsanity.com/paper/2312.15297/) (2023)
- [(Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models](https://mlsanity.com/paper/2409.02628/) (2024)
- [DEBOSH: Deep Bayesian Shape Optimization](https://mlsanity.com/paper/2109.13337/) (2021)
- [A Reliable and Interpretable Framework of Multi-view Learning for Liver Fibrosis Staging](https://mlsanity.com/paper/2306.12054/) (2023)
- [MERIT: Multi-view evidential learning for reliable and interpretable liver fibrosis staging](https://mlsanity.com/paper/2405.02918/) (2024)
- [Enabling Uncertainty Estimation in Iterative Neural Networks](https://mlsanity.com/paper/2403.16732/) (2024)
- [Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation](https://mlsanity.com/paper/2412.03178/) (2024)
- [Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling](https://mlsanity.com/paper/2302.01312/) (2023)
- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [An Informative Path Planning Framework for Active Learning in UAV-based Semantic Mapping](https://mlsanity.com/paper/2302.03347/) (2023)
- [Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model](https://mlsanity.com/paper/2205.11833/) (2022)
- [Raising the Bar on the Evaluation of Out-of-Distribution Detection](https://mlsanity.com/paper/2209.11960/) (2022)
- [Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation](https://mlsanity.com/paper/2412.07169/) (2024)
- [Learning Credal Ensembles via Distributionally Robust Optimization](https://mlsanity.com/paper/2602.08470/) (2026)
- [Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning](https://mlsanity.com/paper/2312.10116/) (2023)
- [Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2312.10390/) (2023)
- [IT3: Idempotent Test-Time Training](https://mlsanity.com/paper/2410.04201/) (2024)
- [OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction](https://mlsanity.com/paper/2503.10605/) (2025)
- [Ex uno plures: Splitting One Model into an Ensemble of Subnetworks](https://mlsanity.com/paper/2106.04767/) (2021)

## Abstract (arXiv)

Deep neural networks have amply demonstrated their prowess but estimating the reliability of their predictions remains challenging. Deep Ensembles are widely considered as being one of the best methods for generating uncertainty estimates but are very expensive to train and evaluate. MC-Dropout is another popular alternative, which is less expensive, but also less reliable. Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples. The first uses an effectively infinite number of highly correlated models while the second relies on a finite number of independent models. To combine the benefits of both, we introduce Masksembles. Instead of randomly dropping parts of the network as in MC-dropout, Masksemble relies on a fixed number of binary masks, which are parameterized in a way that allows to change correlations between individual models. Namely, by controlling the overlap between the masks and their density one can choose the optimal configuration for the task at hand. This leads to a simple and easy to implement method with performance on par with Ensembles at a fraction of the cost. We experimentally validate Masksembles on two widely used datasets, CIFAR10 and ImageNet.