Forgetting in incremental Faster R-CNN comes mainly from the RoI classification head; replaying coarse and fine RoI feature prototypes plus null-space gradient projection reduces forgetting and raises old-class mAP.
On PASCAL VOC dataset, we train the network with SGD optimizer, momentum of 0.9 and weight decay of 10e-4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
Forgetting in incremental Faster R-CNN comes mainly from the RoI classification head; replaying coarse and fine RoI feature prototypes plus null-space gradient projection reduces forgetting and raises old-class mAP.