Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning
PolyMem, an exemplar-free approach that implicitly models rich high-order statistics of the feature distribution to enhance cross-domain robustness, is introduced that effectively alleviates the performance discrepancy while improving the model's performance across domains.
Jin-Ge Ma, Gautham Vinod, Bruce Coburn et al.
· 0 citations