Global ETD Search

Label-Efficient and Compute-Efficient Video Analytics

Bastani, FavyenMassachusetts Institute of Technology2021

… such as cars and birds. These models are both label-intensive, often requiring thousands of labeled examples to achieve high-accuracy, and compute-intensive, executing at tens of frames per second even on datacenter GPUs. Second, in addition to applying ML models, these tasks often require …

mit Repository record for Label-Efficient and Compute-Efficient Video Analytics (opens in a new tab)

Label-Efficient Visual Understanding with Consistency Constraints

Zou, YuliangVirginia Tech2022

… tasks, as long as a sufficiently large labeled dataset is available during the training time. However, the progress of these visual tasks is limited by the number of manual annotations. On the other hand, it is usually time-consuming and error-prone to annotate visual data, rendering the …

vt Repository record for Label-Efficient Visual Understanding with Consistency Constraints (opens in a new tab)

Towards Label-Efficient Learning: Exploiting Limited Labels and Abundant Unlabeled Data

Henry Peng Zou (24399515)2026

Efficiently exploiting limited labels alongside abundant unlabeled data is critical for advancing the capabilities of language models and their downstream systems. This thesis first presents novel methodologies for label-efficient learning, introducing three frameworks: (1) JointMatch, which …

uic

Label-efficient anomaly detection for industrial process-health monitoring : optimising classification strategy and cross-machine augmentation under extreme class imbalance

Bonth, K. de2025

tilburg Repository record for Label-efficient anomaly detection for industrial process-health monitoring : optimising classification strategy and cross-machine augmentation under extreme class imbalance (opens in a new tab)

Towards Scalable Structured Data from Clinical Text

Agrawal, MonicaMassachusetts Institute of Technology2023

… hundreds of notes, and there is often minimal labeled data. In this thesis, I tackle these barriers from three interconnected angles: (i) the design of human-AI teams to speed up annotation workflows, (ii) the development of label-efficient modeling methods, and (iii) a re-design of electronic …

mit Repository record for Towards Scalable Structured Data from Clinical Text (opens in a new tab)

Toward effective and generalisable machine learning for biosignal time series

Wu, YuUniversity of Cambridge2025

… contain missing values, and lack sufficient labels. In contrast, existing state-of-the-art methods are typically developed and validated on clean, regularly sampled biosignals with clinically verified ground-truth annotations, which limits their effectiveness and leads to performance …

cambridge Repository record for Toward effective and generalisable machine learning for biosignal time series (opens in a new tab)