Search papers, labs, and topics across Lattice.
3
0
3
Attribution regularization can dramatically improve model robustness to geometric transformations with minimal impact on accuracy.
Unreliable pseudo-labels in object detection can be transformed into reliable training signals, leading to substantial performance gains across domains.
PhaseWin slashes the computational cost of visual attribution from quadratic to linear while preserving high faithfulness, revolutionizing how we interpret model decisions.
