HMDRN combines dual-layer feature reconstruction with a binary-mask transformer to achieve state-of-the-art few-shot fine-grained classification on CUB, Dogs, and Cars.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification
HMDRN combines dual-layer feature reconstruction with a binary-mask transformer to achieve state-of-the-art few-shot fine-grained classification on CUB, Dogs, and Cars.