Search papers, labs, and topics across Lattice.
3
0
5
8
Saliency-driven prototype alignment can dramatically enhance dataset distillation, yielding better generalization and performance in complex visual tasks.
Pre-training objectives shape how ViTs encode geometric information, revealing that some models can compress dense geometric signals without sacrificing performance.
Current anomaly detection benchmarks are too easily fooled by visual noise; VID-AD offers a rigorous new testbed to isolate and address this weakness.
