Anchor Diffusion for Unsupervised Video Object Segmentation
arXiv:1910.10895
Abstract
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow. Despite their complexity, these kinds of approaches tend to favour short-term temporal dependencies and are thus prone to accumulating inaccuracies, which cause drift over time. Moreover, simple (static) image segmentation models, alone, can perform competitively against these methods, which further suggests that the way temporal dependencies are modelled should be reconsidered. Motivated by these observations, in this paper we explore simple yet effective strategies to model long-term temporal dependencies. Inspired by the non-local operators of [70], we introduce a technique to establish dense correspondences between pixel embeddings of a reference "anchor" frame and the current one. This allows the learning of pairwise dependencies at arbitrarily long distances without conditioning on intermediate frames. Without online supervision, our approach can suppress the background and precisely segment the foreground object even in challenging scenarios, while maintaining consistent performance over time. With a mean IoU of , our method ranks first on the DAVIS-2016 leaderboard of unsupervised methods, while still being competitive against state-of-the-art online semi-supervised approaches. We further evaluate our method on the FBMS dataset and the ViSal video saliency dataset, showing results competitive with the state of the art.
To appear in ICCV 2019
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- Rethinking Atrous Convolution for Semantic Image Segmentation
- On the difficulty of training Recurrent Neural Networks
- Semantic Instance Segmentation via Deep Metric Learning
- The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation
- Video Object Segmentation with Re-identification