Weakly-Supervised Semantic Segmentation using Motion Cues

Abstract : Fully convolutional neural networks (FCNNs) trained on a large number of images with strong pixel-level annotations have become the new state of the art for the semantic segmentation task. While there have been recent attempts to learn FCNNs from image-level weak annotations , they need additional constraints, such as the size of an object , to obtain reasonable performance. To address this issue, we present motion-CNN (M-CNN), a novel FCNN framework which incorporates motion cues and is learned from video-level weak annotations. Our learning scheme to train the network uses motion segments as soft constraints, thereby handling noisy motion information. When trained on weakly-annotated videos, our method outperforms the state-of-the-art approach on the PASCAL VOC 2012 image segmentation benchmark. We also demonstrate that the performance of M-CNN learned with 150 weak video annotations is on par with state-of-the-art weakly-supervised methods trained with thousands of images. Finally, M-CNN substantially out-performs recent approaches in a related task of video co-localization on the YouTube-Objects dataset.
Liste complète des métadonnées

Cited literature [39 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01292794
Contributor : Thoth Team <>
Submitted on : Tuesday, August 2, 2016 - 5:26:12 PM
Last modification on : Monday, May 28, 2018 - 3:10:06 PM
Document(s) archivé(s) le : Tuesday, November 8, 2016 - 8:45:09 PM

File

mcnn.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Pavel Tokmakov, Karteek Alahari, Cordelia Schmid. Weakly-Supervised Semantic Segmentation using Motion Cues. ECCV - European Conference on Computer Vision, Oct 2016, Amsterdam, Netherlands. pp.388-404, ⟨10.1007/978-3-319-46493-0_24⟩. ⟨hal-01292794v3⟩

Share

Metrics

Record views

1704

Files downloads

1307