PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings

no code implementations • 21 Nov 2022 • Nikita Durasov, Nik Dorndorf, Pascal Fua

Active Learning (AL) can be used to reduce this burden.

Active Learning Multi-Task Learning

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

no code implementations • 21 Nov 2022 • Nikita Durasov, Nik Dorndorf, Hieu Le, Pascal Fua

Sampling-free approaches can be faster but suffer from other drawbacks, such as lower reliability of uncertainty estimates, difficulty of use, and limited applicability to different types of tasks and data.

Vocal Bursts Valence Prediction