Multi-route training with instructive self-attention tokens and a route-aware mixture-of-experts raises detection mAP by 2 to 4 points across several DETR baselines at no inference cost.
Mr. detr: Instructive multi-route training for detection transformers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts
Multi-route training with instructive self-attention tokens and a route-aware mixture-of-experts raises detection mAP by 2 to 4 points across several DETR baselines at no inference cost.