Unsupervised Salient Object Detection with Spectral Cluster Voting

Autor:	Shin, Gyungin, Albanie, Samuel, Xie, Weidi
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We make the following contributions: (i) We revisit spectral clustering and demonstrate its potential to group the pixels of salient objects; (ii) Given mask proposals from multiple applications of spectral clustering on image features computed from various self-supervised models, e.g., MoCov2, SwAV, DINO, we propose a simple but effective winner-takes-all voting mechanism for selecting the salient masks, leveraging object priors based on framing and distinctiveness; (iii) Using the selected object segmentation as pseudo groundtruth masks, we train a salient object detector, dubbed SelfMask, which outperforms prior approaches on three unsupervised SOD benchmarks. Code is publicly available at https://github.com/NoelShin/selfmask. Comment: 14 pages, 5 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.12614 Zobrazit plný text záznamu View this record from Arxiv