Skip to Main content Skip to Navigation
Conference papers

Local Propagation for Few-Shot Learning

Abstract : The challenge in few-shot learning is that available data is not enough to capture the underlying distribution. To mitigate this, two emerging directions are (a) using local image representations, essentially multiplying the amount of data by a constant factor, and (b) using more unlabeled data, for instance by transductive inference, jointly on a number of queries. In this work, we bring these two ideas together, introducing local propagation. We treat local image features as independent examples, we build a graph on them and we use it to propagate both the features themselves and the labels, known and unknown. Interestingly, since there is a number of features per image, even a single query gives rise to transductive inference. As a result, we provide a universally safe choice for few-shot inference under both non-transductive and transductive settings, improving accuracy over corresponding methods. This is in contrast to existing solutions, where one needs to choose the method depending on the quantity of available data.
Document type :
Conference papers
Complete list of metadata
Contributor : Yannis Avrithis Connect in order to contact the contributor
Submitted on : Tuesday, December 8, 2020 - 9:34:16 PM
Last modification on : Tuesday, October 19, 2021 - 11:04:41 AM
Long-term archiving on: : Tuesday, March 9, 2021 - 8:15:10 PM


Files produced by the author(s)


  • HAL Id : hal-03047534, version 1


Yann Lifchitz, Yannis Avrithis, Sylvaine Picard. Local Propagation for Few-Shot Learning. ICPR 2020 - 25th International Conference on Pattern Recognition, Jan 2021, Virtual, Italy. pp.1-8. ⟨hal-03047534⟩



Record views


Files downloads