Predicting Future Instance Segmentation by Forecasting Convolutional Features - Archive ouverte HAL Access content directly
Conference Papers Year :

Predicting Future Instance Segmentation by Forecasting Convolutional Features

(1) , (1) , (2) , (3)
1
2
3

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 segmentation, which additionally segments out individual objects. To deal with a varying number of output labels per image, we develop a predictive 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 strong baselines based on optical flow and repurposed instance segmentation architectures.
Fichier principal
Vignette du fichier
luc18eccv_arxiv.pdf (7.36 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01757669 , version 1 (03-04-2018)
hal-01757669 , version 2 (03-10-2018)

Identifiers

Cite

Pauline Luc, Camille Couprie, Yann Lecun, Jakob Verbeek. Predicting Future Instance Segmentation by Forecasting Convolutional Features. ECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.593-608, ⟨10.1007/978-3-030-01240-3_36⟩. ⟨hal-01757669v2⟩
882 View
1150 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More