2021/11/11 by Nikita Araslanov, Simone Schaub-Meyer, Araslanov, Nikita +3 · 4 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Visual Attention and Saliency Detection
paper · doi:10.48550/arxiv.2111.06265
openalex publication_date 2021/11/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29
We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling to extract a set of anchors and train our model to disambiguate between them on both inter- and intra-video levels. However, a naive scheme to train such a model results in a degenerate solution. We propose to prevent this with a simple regularisation scheme, accommodating the equivariance property of the segmentation task to similarity transformations. Our training objective admits efficient implementation and exhibits fast training convergence. On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.