Ensemble Foreground Management for Unsupervised Object Discovery
(2025)
Presentation / Conference Contribution
Wu, Z., Moemeni, A., & Caleb-Solly, P. (2025, October). Ensemble Foreground Management for Unsupervised Object Discovery. Presented at International Conference on Computer Vision ICCV 2025, Honolulu, Hawai'i
Unsupervised object discovery (UOD) aims to detect and segment objects in 2D images without handcrafted anno- tations. Recent progress in self-supervised representation learning [9, 66] has led to some success in UOD algo- rithms [21, 53, 69]. Howeve... Read More about Ensemble Foreground Management for Unsupervised Object Discovery.