Abstract
Recent progress in multimodal, high-dimensional learning has enabled foundation models to process heterogeneous, large-scale data. However, at test time, acquiring all features or modalities can be prohibitively costly and often redundant. Sequentially selecting informative modalities is therefore critical, yet challenging when the downstream task or prediction target is unknown. To this end, we introduce ECHO-$k$, a task-agnostic and self-supervised learning principle for modality acquisition: we use a deep model's internal pretrained representations (e.g., from a foundation model) as proxy targets that summarize cross-modal information. We provide theoretical guarantees in a stylized linear setting that motivate a reinforcement learning (RL) policy for sequential modality selection. Across task-agnostic and label-free acquisition baselines, ECHO-$k$ consistently improves budgeted downstream performance across diverse foundation-model backends. Our method provides a principled route to cost-aware test-time deployment, with implications for any multimodal system where measurements are expensive or time-constrained, and downstream tasks unknown a priori.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Jain, E., Bleistein, L., Deplancke, B., & Bunne, C. (2026). Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition. https://omanscience.com/en/articles/measure-less-know-more-self-supervised-test-time-feature-acquisition
MLA 9
Jain, Eeshaan, et al. "Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition." https://omanscience.com/en/articles/measure-less-know-more-self-supervised-test-time-feature-acquisition.
Chicago (author–date)
Jain, Eeshaan, Linus Bleistein, Bart Deplancke, and Charlotte Bunne. 2026. "Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition." https://omanscience.com/en/articles/measure-less-know-more-self-supervised-test-time-feature-acquisition.
Harvard
Jain, E., Bleistein, L., Deplancke, B. and Bunne, C. (2026) 'Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition', Available at: https://omanscience.com/en/articles/measure-less-know-more-self-supervised-test-time-feature-acquisition.
Vancouver
Jain E, Bleistein L, Deplancke B, Bunne C. Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition. https://omanscience.com/en/articles/measure-less-know-more-self-supervised-test-time-feature-acquisition
IEEE
E. Jain, L. Bleistein, B. Deplancke, and C. Bunne, "Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition," https://omanscience.com/en/articles/measure-less-know-more-self-supervised-test-time-feature-acquisition.