A decoder transformer with learnable queries plus a low-rank parallel adapter for frozen DINOv2 achieves state-of-the-art visual place recognition on multiple benchmarks with reduced training memory.
Mapillary street-level sequences: A dataset for lifelong place JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13 recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
EDTformer: An Efficient Decoder Transformer for Visual Place Recognition
A decoder transformer with learnable queries plus a low-rank parallel adapter for frozen DINOv2 achieves state-of-the-art visual place recognition on multiple benchmarks with reduced training memory.