Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learning
This addresses the problem of efficient video object segmentation for applications requiring real-time processing, though it appears incremental as it builds on existing embedding and retrieval approaches.
This paper tackles video object segmentation by formulating it as pixel-wise retrieval in a learned embedding space, achieving competitive state-of-the-art results with significantly reduced computation cost (275 milliseconds per frame) in semi-supervised scenarios and instant response in interactive scenarios.
This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance into the vicinity of each other, using a fully convolutional network trained by a modified triplet loss as the embedding model. Then the annotated pixels are set as reference and the rest of the pixels are classified using a nearest-neighbor approach. The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario). In the semi-supervised scenario, we achieve results competitive with the state of the art but at a fraction of computation cost (275 milliseconds per frame). In the interactive scenario where the user is able to refine their input iteratively, the proposed method provides instant response to each input, and reaches comparable quality to competing methods with much less interaction.