Logga in
insikt - Unsupervised Object Discovery
CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers
The authors introduce VoteCut and CuVLER, innovative methods for unsupervised object discovery and segmentation, showcasing significant improvements over previous state-of-the-art models.
CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers
VoteCut and CuVLER revolutionize unsupervised object discovery with self-supervised transformers.
Unsupervised Object Discovery through Masked Multi-Query Slot Attention
Unsupervised object discovery can be improved by selectively masking background regions during training and using multi-query slot attention to learn more stable and generalizable object representations.
Produkter | Resurser
© 2024 by Linnk AI