header

Profile


photo

Sebastian Hennen



Publications


Making a Case for 3D Convolutions for Object Segmentation in Videos


Sabarinath Mahadevan, Ali Athar, Aljoša Ošep, Sebastian Hennen, Laura Leal-Taixé, Bastian Leibe
British Machine Vision Conference (BMVC'20)
pubimg

The task of object segmentation in videos is usually accomplished by processing appearance and motion information separately using standard 2D convolutional networks, followed by a learned fusion of the two sources of information. On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos compared to their 2D convolutional counterparts and lag behind the aforementioned networks in terms of performance. In this work, we show that 3D CNNs can be effectively applied to dense video prediction tasks such as salient object segmentation. We propose a simple yet effective encoder-decoder network architecture consisting entirely of 3D convolutions that can be trained end-to-end using a standard cross-entropy loss. To this end, we leverage an efficient 3D encoder, and propose a 3D decoder architecture, that comprises novel 3D Global Convolution layers and 3D Refinement modules. Our approach outperforms existing state-of-the-arts by a large margin on the DAVIS'16 Unsupervised, FBMS and ViSal dataset benchmarks in addition to being faster, thus showing that our architecture can efficiently learn expressive spatio-temporal features and produce high quality video segmentation masks.

» Show Videos
» Show BibTeX

@inproceedings{Mahadevan20BMVC,
title={Making a Case for 3D Convolutions for Object Segmentation in Videos},
author={Mahadevan, Sabarinath and Athar, Ali and O{\v{s}}ep, Aljo{\v{s}}a and Hennen, Sebastian and Leal-Taix{\'e}, Laura and Leibe, Bastian},
booktitle={BMVC},
year={2020}
}





Disclaimer Home Visual Computing institute RWTH Aachen University