Parameter-efficient fine-tuning (LoRA family)
Cascade R-CNN
Cascade R-CNN: Delving into High Quality Object Detection
Superseded baseline#256 of 1,113 most-superseded · first seen Dec 3, 2017
Superseded — cited as a baseline and beaten by newer methods
0 papers critique it · 1 beat it on benchmarks
Beaten on benchmarks
Head-to-head results where a newer method reports beating Cascade R-CNN. Values are copied from the source paper's tables — verify against the cited paper.
LMA beats Cascade R-CNN
65.7 vs 59.6
mAP · [Visible+Infrared]
FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network
What to use instead
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.