Weakly-supervised learning of visual relations - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Weakly-supervised learning of visual relations


This paper introduces a novel approach for modeling visual relations between pairs of objects. We call relation a triplet of the form (subject, predicate, object) where the predicate is typically a preposition (eg. 'under', 'in front of') or a verb ('hold', 'ride') that links a pair of objects (subject, object). Learning such relations is challenging as the objects have different spatial configurations and appearances depending on the relation in which they occur. Another major challenge comes from the difficulty to get annotations , especially at box-level, for all possible triplets, which makes both learning and evaluation difficult. The contributions of this paper are threefold. First, we design strong yet flexible visual features that encode the appearance and spatial configuration for pairs of objects. Second, we propose a weakly-supervised discriminative clustering model to learn relations from image-level labels only. Third we introduce a new challenging dataset of unusual relations (UnRel) together with an exhaustive annotation, that enables accurate evaluation of visual relation retrieval. We show experimentally that our model results in state-of-the-art results on the visual relationship dataset [31] significantly improving performance on previously unseen relations (zero-shot learning), and confirm this observation on our newly introduced UnRel dataset.
Fichier principal
Vignette du fichier
weaksup_hal.pdf (5.6 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01576035 , version 1 (22-08-2017)



Julia Peyre, Ivan Laptev, Cordelia Schmid, Josef Sivic. Weakly-supervised learning of visual relations. ICCV 2017- International Conference on Computer Vision 2017, Oct 2017, Venice, Italy. pp.5189-5198, ⟨10.1109/ICCV.2017.554⟩. ⟨hal-01576035⟩
631 View
304 Download



Gmail Facebook X LinkedIn More