Similarity learning for dense label transfer

Conference item

In this work, we introduce a simple and flexible method for video object segmentation based on similarity learning. The proposed method can learn to perform dense label transfer from one image to the other. More specifically, the objective is to learn a similarity metric for dense pixel-wise correspondence between two images. This learned model can then be used in a label transfer framework to propagate object annotations from a reference frame to all the subsequent frames in a video. Unlike previous methods, our similarity learning approach works fairly well across various domains, even when no domain adaptation is involved. Using the proposed approach, we achieved the second place in the first DAVIS challenge for interactive video object segmentation, in both quality and speed tracks.

Authors: Najafi, M; Kulharia, V; Ajanthan, T; Torr, P

• Publication status: Published
• Peer review status: Reviewed (other)
• Host title: 2018 DAVIS Challenge on Video Object Segmentation - CVPR Workshops
• Journal: IEEE
• Acceptance date: 2018-06-07