Deformable DETR achieves higher accuracy than DETR, especially on small objects, while converging in one-tenth the training epochs by using sparse deformable attention on image features.
An empirical study of spatial attention mechanisms in deep networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2020 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Deformable DETR achieves higher accuracy than DETR, especially on small objects, while converging in one-tenth the training epochs by using sparse deformable attention on image features.