MFSC: Matching by Few-Shot Classification
Daniel Shalam (University of Haifa), Elie Abboud (University of Haifa), Roee Litman (-), Simon Korman (University of Haifa)*
The 34th British Machine Vision Conference
Abstract
The ability to accurately and efficiently match between sets of items has always been fundamental in computer vision pipelines and applications with a wide variety of realizations that involve finding correspondences between sets of local features, small patches or entire images collections. In recent years, the emergence of deep learning has facilitated significant improvements of matching based applications. This progress was achieved through advancing improved data embedding and description, and less focus was put on the matching process itself. Specifically, relying on simple pairwise or triplet distance-based metric learning, ignoring the set-to-set nature of the problem. We suggest a holistic approach to matching, by observing its natural connection to few-shot classification (FSC), a largely growing research area that deals with learning using limited amounts of data. We argue that certain popular FSC paradigms, such as meta-learning and transductive learning, are particularly suitable for tackling the specific challenges that arise in matching problems. Our approach, MFSC, builds upon state-of-the-art features and FSC algorithms, significantly improving the quality of matching. Moreover, we show how to construct a meta-learning scheme based on our approach, which allows end-to-end training of the entire matching process. We validate our method on the tasks of patch-correspondence, image-alignment and person re-identification.Video
Citation
@inproceedings{Shalam_2023_BMVC,
author = {Daniel Shalam and Elie Abboud and Roee Litman and Simon Korman},
title = {MFSC: Matching by Few-Shot Classification},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0677.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by