Full-duplex strategy for video object segmentation

Abstract Previous video object segmentation approaches mainly focus on simplex solutions linking appearance and motion, limiting effective feature collaboration between these two cues. In this work, we study a novel efficient full-duplex strategy network ( FSNet ) to address issue, by considering better mutual restraint scheme motion allowing exploitation of cross-modal features from the fusion decoding stage. Specifically, introduce relational cross-attention module (RCAM) achieve bidirectional message propagation across embedding sub-spaces. To improve model’s robustness update inconsistent spatiotemporal embeddings, adopt purification after RCAM. Extensive experiments five popular benchmarks show that our is robust various challenging scenarios (e.g., blur occlusion), compares well leading methods both for salient detection. The project publicly available at https://github.com/GewelsJI/FSNet .