Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

Xueting Zhang, Debin Meng, Henry Gouk, Timothy Hospedales

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Many state-of-the-art few-shot learners focus on developing effective training procedures for feature representations, before using simple (e.g., nearest centroid) classifiers. We take an approach that is agnostic to the features used, and focus exclusively on meta-learning the final classifier layer. Specifically, we introduce MetaQDA, a Bayesian meta-learning generalisation of the classic quadratic discriminant analysis. This approach has several benefits of interest to practitioners: meta-learning is fast and memory efficient, without the need to fine-tune features. It is agnostic to the off-the-shelf features chosen, and thus will continue to benefit from future advances in feature representations. Empirically, it leads to excellent performance in cross-domain few-shot learning, class-incremental few-shot learning, and crucially for real-world applications, the Bayesian formulation leads to state-of-the-art uncertainty calibration in predictions.
Original languageEnglish
Title of host publicationInternational Conference on Computer Vision (ICCV 2021)
Number of pages12
Publication statusAccepted/In press - 22 Jul 2021
EventInternational Conference on Computer Vision 2021 - Online
Duration: 11 Oct 202117 Oct 2021


ConferenceInternational Conference on Computer Vision 2021
Abbreviated titleICCV 2021
Internet address


Dive into the research topics of 'Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition'. Together they form a unique fingerprint.

Cite this