# Hypothesis Disparity Regularized Mutual Information Maximization

arXiv: https://arxiv.org/abs/2012.08072 · HTML: https://mlsanity.com/paper/2012.08072/

## Key facts

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

## Built on by (most cited first, 15 of 15)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Uncertainty-guided Source-free Domain Adaptation](https://mlsanity.com/paper/2208.07591/) (2022)
- [On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion](https://mlsanity.com/paper/2308.09942/) (2023)
- [UMAD: Universal Model Adaptation under Domain and Category Shift](https://mlsanity.com/paper/2112.08553/) (2021)
- [Proxy Denoising for Source-Free Domain Adaptation](https://mlsanity.com/paper/2406.01658/) (2024)
- [ConDA: Continual Unsupervised Domain Adaptation](https://mlsanity.com/paper/2103.11056/) (2021)
- [On Universal Black-Box Domain Adaptation](https://mlsanity.com/paper/2104.04665/) (2021)
- [A Unified Framework for Heterogeneous Semi-supervised Learning](https://mlsanity.com/paper/2503.00286/) (2025)
- [COLA: Context-aware Language-driven Test-time Adaptation](https://mlsanity.com/paper/2509.17598/) (2025)
- [Source-Free Domain Adaptation with Vision-Language Prior](https://mlsanity.com/paper/2604.17748/) (2026)
- [Source-free Domain Adaptation Requires Penalized Diversity](https://mlsanity.com/paper/2304.02798/) (2023)
- [DRIVE: Dual-Robustness via Information Variability and Entropic Consistency in Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.15976/) (2024)
- [A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2509.22229/) (2025)

## Abstract (arXiv)

We propose a hypothesis disparity regularized mutual information maximization~(HDMI) approach to tackle unsupervised hypothesis transfer -- as an effort towards unifying hypothesis transfer learning (HTL) and unsupervised domain adaptation (UDA) -- where the knowledge from a source domain is transferred solely through hypotheses and adapted to the target domain in an unsupervised manner. In contrast to the prevalent HTL and UDA approaches that typically use a single hypothesis, HDMI employs multiple hypotheses to leverage the underlying distributions of the source and target hypotheses. To better utilize the crucial relationship among different hypotheses -- as opposed to unconstrained optimization of each hypothesis independently -- while adapting to the unlabeled target domain through mutual information maximization, HDMI incorporates a hypothesis disparity regularization that coordinates the target hypotheses jointly learn better target representations while preserving more transferable source knowledge with better-calibrated prediction uncertainty. HDMI achieves state-of-the-art adaptation performance on benchmark datasets for UDA in the context of HTL, without the need to access the source data during the adaptation.