Motion-Attentive Transition for Zero-Shot Video Object Segmentation

Abstract

In this paper, we present a novel Motion-Attentive Transition Network (MATNet) for zero-shot video object segmentation, which provides a new way of leveraging motion information to reinforce spatio-temporal object representation. An asymmetric attention block, called Motion-Attentive Transition (MAT), is designed within a two-stream encoder, which transforms appearance features into motion-attentive representations at each convolutional stage. In this way, the encoder becomes deeply interleaved, allowing for closely hierarchical interactions between object motion and appearance. This is superior to the typical two-stream architecture, which treats motion and appearance separately in each stream and often suffers from overfitting to appearance information. Additionally, a bridge network is proposed to obtain a compact, discriminative and scale-sensitive representation for multi-level encoder features, which is further fed into a decoder to achieve segmentation results. Extensive experiments on three challenging public benchmarks (i.e. DAVIS-16, FBMS and Youtube-Objects) show that our model achieves compelling performance against the state-of-the-arts.

AAAI 2020. Code: https://github.com/tfzhou/MATNet

References in corpus (4)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• Spatiotemporal Residual Networks for Video Action Recognition
• The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation
• Simple vs complex temporal recurrences for video saliency prediction

Cited by in corpus (14)

• Video Polyp Segmentation: A Deep Learning Perspective
• Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation
• EM-driven unsupervised learning for efficient motion segmentation
• Adversarial Attacks on Video Object Segmentation with Hard Region Discovery
• Full-Duplex Strategy for Video Object Segmentation
• Co-attention Propagation Network for Zero-Shot Video Object Segmentation
• Online Unsupervised Video Object Segmentation via Contrastive Motion Clustering
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
• Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
• MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentation
• Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
• DONet: Dual-Octave Network for Fast MR Image Reconstruction
• Towards Imbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation
• Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation