Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
CALIPER is presented, a model-free RGB-D framework that couples support-based appearance matching with metric size evidence and improves unseen-class accuracy by up to 37.4 percentage points without statistically significant degradation of the original inventory.
Generalization across hardware fault severities in automotive radar systems remains a significant challenge, with the best-performing model only achieving 0.663 macro-F1 in controlled conditions.
