Detecting unseen visual relations using analogies project page

People

Abstract

This paper introduces a novel approach for modeling visual relations between pairs of objects. We seek to detect visual relations in images of the form of triplets t=(subject,predicate,object), such as "person riding dog", where training examples of the individual entities are available but their combinations are unseen at training. This is an important set-up due to the combinatorial nature of visual relations : collecting sufficient training data for all possible triplets would be very hard. The contributions of this work are three-fold. First, we learn a representation of visual relations that combines (i) individual embeddings for subject, object and predicate together with (ii) a visual phrase embedding that represents the relation triplet. Second, we learn how to transfer visual phrase embeddings from existing training triplets to unseen test triplets using analogies between relations that involve similar objects. Third, we demonstrate the benefits of our approach on three challenging datasets : on HICO-DET, our model achieves significant improvement over a strong baseline for both frequent and unseen triplets, and we observe similar improvement for the retrieval of unseen triplets with out-of-vocabulary predicates on the COCO-a dataset as well as the challenging unusual triplets in the UnRel dataset.

Paper

[paper] [arXiv]

BibTeX

@InProceedings{Peyre19,
    author      = "Peyre, Julia and Laptev, Ivan and Schmid, Cordelia and Sivic, Josef",
    title       = "Detecting Unseen Visual Relations Using Analogies",
    booktitle   = "ICCV",
    year        = "2019"
}

Code

To run the code, first clone the github project:

[GitHub]

Load the data:

[data]

Load the pre-trained models:

[pretrained_models]

Acknowledgements

This work was partly supported by ERC grants Activia (no.307574), LEAP (no.336845), Allegro (no.320559), CIFAR Learning in Machines & Brains program, the MSR-Inria joint lab, Louis Vuitton ENS Chair on Artificial Intelligence, DGA project DRAAF, and European Regional Development Fund under the project IMPACT (reg. no. CZ.02.1.01/0.0/0.0/15\_003/0000468).