Timezone: »

 
Poster
Re-ranking for image retrieval and transductive few-shot classification
Xi SHEN · Yang Xiao · Shell Xu Hu · Othman Sbai · Mathieu Aubry

Thu Dec 09 12:30 AM -- 02:00 AM (PST) @
in Poster Session 5 »

In the problems of image retrieval and few-shot classification, the mainstream approaches focus on learning a better feature representation. However, directly tackling the distance or similarity measure between images could also be efficient. To this end, we revisit the idea of re-ranking the top-k retrieved images in the context of image retrieval (e.g., the k-reciprocal nearest neighbors) and generalize this idea to transductive few-shot learning. We propose to meta-learn the re-ranking updates such that the similarity graph converges towards the target similarity graph induced by the image labels. Specifically, the re-ranking module takes as input an initial similarity graph between the query image and the contextual images using a pre-trained feature extractor, and predicts an improved similarity graph by leveraging the structure among the involved images. We show that our re-ranking approach can be applied to unseen images and can further boost existing approaches for both image retrieval and few-shot learning problems. Our approach operates either independently or in conjunction with classical re-ranking approaches, yielding clear and consistent improvements on image retrieval (CUB, Cars, SOP, rOxford5K and rParis6K) and transductive few-shot classification (Mini-ImageNet, tiered-ImageNet and CIFAR-FS) benchmarks. Our code is available at https://imagine.enpc.fr/~shenx/SSR/.

Keywords: Machine Learning · Graph Learning · Meta Learning · Few Shot Learning

Author Information

Xi SHEN (Ecole des Ponts ParisTech)
Yang Xiao (ENPC)
Shell Xu Hu (Samsung AI Center Cambridge)
Othman Sbai (Ecole des Ponts)
Mathieu Aubry (École des ponts ParisTech)

More from the Same Authors