# Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

arXiv: https://arxiv.org/abs/2303.00914 · HTML: https://mlsanity.com/paper/2303.00914/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 74 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 30 of 35)

- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [Learning to Optimize Domain Specific Normalization for Domain Generalization](https://mlsanity.com/paper/1907.04275/) (2019)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization](https://mlsanity.com/paper/2112.00463/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Source-Free Domain Adaptation via Distribution Estimation](https://mlsanity.com/paper/2204.11257/) (2022)
- [Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules](https://mlsanity.com/paper/1801.05219/) (2018)
- [Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes](https://mlsanity.com/paper/2207.11707/) (2022)
- [Unsupervised Learning by Competing Hidden Units](https://mlsanity.com/paper/1806.10181/) (2018)
- [Domain Generalization via Inference-time Label-Preserving Target Projections](https://mlsanity.com/paper/2103.01134/) (2021)
- [Test-Time Personalization with a Transformer for Human Pose Estimation](https://mlsanity.com/paper/2107.02133/) (2021)

## Built on by (most cited first, 23 of 23)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2410.12790/) (2024)
- [Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation](https://mlsanity.com/paper/2311.13209/) (2023)
- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation](https://mlsanity.com/paper/2311.01034/) (2023)
- [HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation](https://mlsanity.com/paper/2403.12033/) (2024)
- [Cross-Modal Concept Learning and Inference for Vision-Language Models](https://mlsanity.com/paper/2307.15460/) (2023)
- [Bag of Tricks for Fully Test-Time Adaptation](https://mlsanity.com/paper/2310.02416/) (2023)
- [Learning Visual Conditioning Tokens to Correct Domain Shift for Fully Test-time Adaptation](https://mlsanity.com/paper/2406.19341/) (2024)
- [Temporal Test-Time Adaptation with State-Space Models](https://mlsanity.com/paper/2407.12492/) (2024)
- [Cross-Inferential Networks for Source-free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2306.16957/) (2023)
- [Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2503.09394/) (2025)
- [Unsupervised Prototype Adapter for Vision-Language Models](https://mlsanity.com/paper/2308.11507/) (2023)
- [Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation](https://mlsanity.com/paper/2408.13983/) (2024)
- [Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation](https://mlsanity.com/paper/2312.08378/) (2023)
- [Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics](https://mlsanity.com/paper/2501.06762/) (2025)
- [Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2510.19802/) (2025)
- [Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment](https://mlsanity.com/paper/2405.07171/) (2024)
- [Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks](https://mlsanity.com/paper/2505.05375/) (2025)
- [Gradient-Map-Guided Adaptive Domain Generalization for Cross Modality MRI Segmentation](https://mlsanity.com/paper/2311.09737/) (2023)
- [Neuron-centric Hebbian Learning](https://mlsanity.com/paper/2403.12076/) (2024)
- [Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation](https://mlsanity.com/paper/2512.12673/) (2025)
- [In-Loop Model Adaptation with Coupled Latent-Noise Guidance for High-Fidelity Subject-Driven Text-to-Image Generation](https://mlsanity.com/paper/2608.09244/) (2026)

## Abstract (arXiv)

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. We take inspiration from the biological plausibility learning where the neuron responses are tuned based on a local synapse-change procedure and activated by competitive lateral inhibition rules. Based on these feed-forward learning rules, we design a soft Hebbian learning process which provides an unsupervised and effective mechanism for online adaptation. We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuro-modulation layer. It is able to fine-tune the neuron responses based on the external feedback generated by the error back-propagation from the top inference layers. This leads to our proposed neuro-modulated Hebbian learning (NHL) method for fully test-time adaptation. With the unsupervised feed-forward soft Hebbian learning being combined with a learned neuro-modulator to capture feedback from external responses, the source model can be effectively adapted during the testing process. Experimental results on benchmark datasets demonstrate that our proposed method can significantly improve the adaptation performance of network models and outperforms existing state-of-the-art methods.