Predicting Future Instance Segmentations by Forecasting Convolutional Features

Abstract : Anticipating future events is an important prerequisite towards intelligent behavior. Video forecasting has been studied as a proxy task towards this goal. Recent work has shown that to predict semantic segmentation of future frames, forecasting at the semantic level is more effective than forecasting RGB frames and then segmenting these. In this paper we consider the more challenging problem of future instance seg-mentation, which additionally segments out individual objects. To deal with a varying number of output labels per image, we develop a pre-dictive model in the space of fixed-sized convolutional features of the Mask R-CNN instance segmentation model. We apply the " detection head " of Mask R-CNN on the predicted features to produce the instance segmentation of future frames. Experiments show that this approach significantly improves over baselines based on optical flow.
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01757669
Contributeur : Pauline Luc <>
Soumis le : mardi 3 avril 2018 - 19:00:24
Dernière modification le : lundi 30 avril 2018 - 15:02:01

Fichier

luc2018instpred.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01757669, version 1

Collections

Citation

Pauline Luc, Camille Couprie, Yann Lecun, Jakob Verbeek. Predicting Future Instance Segmentations by Forecasting Convolutional Features. 2018. 〈hal-01757669〉

Partager

Métriques

Consultations de la notice

360

Téléchargements de fichiers

169