Video object segmentation (VOS) is a critical yet challenging task in video analysis. Recently, many pixel-level matching VOS methods have achieved an outstanding performance without significant time consumption in fine-tuning. However, most of these methods pay little attention to (i) matching background pixels and (ii) optimizing discriminable embeddings between classes. To address these issues, we propose a new end-to-end trainable method, namely Triplet Matching for efficient semi-supervised Video Object Segmentation (TMVOS). In particular, we devise a new triplet matching strategy that considers both the foreground and background matching and pulls the nearest negative embedding further than the nearest positive one for every anchor. As a result, this method implicitly enlarges the distances between embeddings of different classes and thereby generates accurate matching maps. Additionally, a dual decoder is applied for optimizing the final segmentation so that the model better fits the complex background and relatively simple targets. Extensive experiments demonstrate that the proposed method achieves superior performance in terms of accuracy and running-time compared with the state-of-the-art methods.
Bibliographical noteFunding Information:
This research was partially supported by the National Natural Science Foundation of China ( 11627802 , 11872185 and 12172134 ), by the State Scholarship Fund of China Scholarship Council ( 201806155 022 ), by the State Key Lab of Subtropical Building Science, South China University of Technology ( 2018ZB33 ), and by Macao Science and Technology Development Fund under Macao Funding Scheme for Key R & D Projects ( 0025/2019/AKP ).
© 2022 Elsevier B.V.
- Embedding learning
- Triplet matching
- Video object segmentation