Deep Layer Aggregation

Fisher YuDequan WangEvan ShelhamerTrevor Darrell

   Papers with code   Abstract  PDF

Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not enough: compounding and aggregating these representations improves inference of what and where... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
DLA-X2-102
79.5%
--
5
DLA-X-102
78.5%
--
15
DLA-X-60-C
69.0%
--
17
DLA-X-46-C
66.7%
--
19
DLA-46-C
65.7%
--