Learning Motion and Temporal Cues for Unsupervised Video Object Segmentation

Abstract

In this paper, we address the challenges in unsupervised video object segmentation (UVOS) by proposing an efficient algorithm, termed MTNet, which concurrently exploits motion and temporal cues. Unlike previous methods that focus solely on integrating appearance with motion or on modeling temporal relations, our method combines both aspects by integrating them within a unified framework. MTNet is devised by effectively merging appearance and motion features during the feature extraction process within encoders, promoting a more complementary representation. To capture the intricate long-range contextual dynamics and information embedded within videos, a temporal transformer module is introduced, facilitating efficacious inter-frame interactions throughout a video clip. Furthermore, we employ a cascade of decoders all feature levels across all feature levels to optimally exploit the derived features, aiming to generate increasingly precise segmentation masks. As a result, MTNet provides a strong and compact framework that explores both temporal and cross-modality knowledge to robustly localize and track the primary object accurately in various challenging scenarios efficiently. Extensive experiments across diverse benchmarks conclusively show that our method not only attains state-of-the-art performance in unsupervised video object segmentation but also delivers competitive results in video salient object detection. These findings highlight the method's robust versatility and its adeptness in adapting to a range of segmentation tasks. Source code is available on https://github.com/hy0523/MTNet.

Accepted to IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

References in corpus (18)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Fully Convolutional Networks for Semantic Segmentation
• Squeeze-and-Excitation Networks
• Is Space-Time Attention All You Need for Video Understanding?
• Video Enhancement with Task-Oriented Flow
• Mixed Precision Training
• Video Salient Object Detection via Fully Convolutional Networks
• Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
• The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation
• Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
• Video Instance Segmentation using Inter-Frame Communication Transformers
• Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation
• Full-Duplex Strategy for Video Object Segmentation
• A Survey on Deep Learning Technique for Video Segmentation
• FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation
• Dual Prototype Attention for Unsupervised Video Object Segmentation
• Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation

Cited by in corpus (1)

• RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation