# MITA: Bridging the Gap between Model and Data for Test-time Adaptation

arXiv: https://arxiv.org/abs/2410.09398 · HTML: https://mlsanity.com/paper/2410.09398/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 12 Oct 2024.

## Builds on (most cited first, 29 of 29)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One](https://mlsanity.com/paper/1912.03263/) (2019)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [How to Train Your Energy-Based Models](https://mlsanity.com/paper/2101.03288/) (2021)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization](https://mlsanity.com/paper/2112.00463/) (2021)
- [Improved Contrastive Divergence Training of Energy Based Models](https://mlsanity.com/paper/2012.01316/) (2020)
- [Back to the Source: Diffusion-Driven Test-Time Adaptation](https://mlsanity.com/paper/2207.03442/) (2022)
- [Controllable and Compositional Generation with Latent-Space Energy-Based Models](https://mlsanity.com/paper/2110.10873/) (2021)
- [Balancing Discriminability and Transferability for Source-Free Domain Adaptation](https://mlsanity.com/paper/2206.08009/) (2022)
- [Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Model](https://mlsanity.com/paper/1812.10907/) (2018)
- [JEM++: Improved Techniques for Training JEM](https://mlsanity.com/paper/2109.09032/) (2021)
- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [Conditional GANs with Auxiliary Discriminative Classifier](https://mlsanity.com/paper/2107.10060/) (2021)
- [Energy-Based Test Sample Adaptation for Domain Generalization](https://mlsanity.com/paper/2302.11215/) (2023)
- [Training Energy-Based Models with Diffusion Contrastive Divergences](https://mlsanity.com/paper/2307.01668/) (2023)
- [Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective](https://mlsanity.com/paper/2211.10929/) (2022)
- [Augmentation-Aware Self-Supervision for Data-Efficient GAN Training](https://mlsanity.com/paper/2205.15677/) (2022)
- [PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion](https://mlsanity.com/paper/2305.15835/) (2023)

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

- [Inference-time Alignment in Continuous Space](https://mlsanity.com/paper/2505.20081/) (2025)

## Abstract (arXiv)

Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. However, existing mainstream TTA methods, predominantly operating at batch level, often exhibit suboptimal performance in complex real-world scenarios, particularly when confronting outliers or mixed distributions. This phenomenon stems from a pronounced over-reliance on statistical patterns over the distinct characteristics of individual instances, resulting in a divergence between the distribution captured by the model and data characteristics. To address this challenge, we propose Meet-In-The-Middle based Test-Time Adaptation (MITA), which introduces energy-based optimization to encourage mutual adaptation of the model and data from opposing directions, thereby meeting in the middle. MITA pioneers a significant departure from traditional approaches that focus solely on aligning the model to the data, facilitating a more effective bridging of the gap between model's distribution and data characteristics. Comprehensive experiments with MITA across three distinct scenarios (Outlier, Mixture, and Pure) demonstrate its superior performance over SOTA methods, highlighting its potential to significantly enhance generalizability in practical applications.