LCN-4 augments ConvNet-4 with grid position encoding and frequency-domain location embedding to achieve state-of-the-art or better results than deeper backbones in fine-grained few-shot classification.
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learning
LCN-4 augments ConvNet-4 with grid position encoding and frequency-domain location embedding to achieve state-of-the-art or better results than deeper backbones in fine-grained few-shot classification.