Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Provable guarantees for self-supervised deep learning with spectral contrastive loss

Provable guarantees for self-supervised deep learning with spectral contrastive loss

US Patent 12423961 · Granted Sep 23, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Self extrinsic self-calibration via geometrically consistent self-supervised dep2025
Systems and methods for multi-object tracking2025
Geometric 3D augmentations for transformer architectures2025
Systems and methods for dynamics-aware comparison of reward functions2025
Systems and methods for depth synthesis with transformer architectures2025
Representation learning for object detection from unlabeled point cloud sequence2025
Adversarial object-aware neural scene rendering for 3D object detection2025
Method and system for learning reward functions for driving using positive-unlab2025
Systems and methods for generic visual odometry using learned features via neura2025
Monocular object detection via end-to-end differentiable pipeline2025
Self-supervised monocular depth estimation via rigid-motion embeddings2025
System and method for self-supervised monocular ground-plane extraction2025