Abstract: As a front-burner problem in incremental learning, class incremental semantic segmentation (CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods have ...
Abstract: Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the prediction logits due to its inefficiency in distilling the ...
(New users only) Unlock 4%* + 10%* p.a. promo rate for 3 months and enjoy FREE RM10 & when you sign up using code VERSAMM10 with min. cash of RM100 today! T&Cs apply. KUALA LUMPUR, Dec 18 — Addressing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback