# Uncertainty-Aware Decomposed Hybrid Networks

arXiv: https://arxiv.org/abs/2503.19096 · HTML: https://mlsanity.com/paper/2503.19096/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging](https://mlsanity.com/paper/2202.05265/) (2022)
- [Towards causal benchmarking of bias in face analysis algorithms](https://mlsanity.com/paper/2007.06570/) (2020)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [Confidence Propagation through CNNs for Guided Sparse Depth Regression](https://mlsanity.com/paper/1811.01791/) (2018)
- [Local Binary Convolutional Neural Networks](https://mlsanity.com/paper/1608.06049/) (2016)
- [Scaling the Scattering Transform: Deep Hybrid Networks](https://mlsanity.com/paper/1703.08961/) (2017)
- [Two decades of local binary patterns: A survey](https://mlsanity.com/paper/1612.06795/) (2016)
- [Physics-based Shading Reconstruction for Intrinsic Image Decomposition](https://mlsanity.com/paper/2009.01540/) (2020)
- [A Vision Architecture](https://mlsanity.com/paper/1407.1642/) (2014)
- [Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning](https://mlsanity.com/paper/2401.08603/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories](https://mlsanity.com/paper/2510.17381/) (2025)

## Abstract (arXiv)

The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks with the interpretability, transparency, and robustness of domain-specific quasi-invariant operators. Our method decomposes the recognition into multiple task-specific operators that focus on different characteristics, supported by a novel confidence measurement tailored to these operators. This measurement enables the network to prioritize reliable features and accounts for noise. We argue that our design enhances transparency and robustness, leading to improved performance, particularly in low-data regimes. Experimental results in traffic sign detection highlight the effectiveness of the proposed method, especially in semi-supervised and unsupervised scenarios, underscoring its potential for data-constrained applications.