ARF-SFR-Net adaptively sizes receptive fields in spatial and frequency branches and reconstructs query features from support features, reporting state-of-the-art few-shot fine-grained accuracy on five benchmarks.
arXiv preprint arXiv:2106.06988 (2021)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
GloResNet, a ResNet-10-based lightweight 3D CNN pretrained on MedicalNet with global manifold mapping for topology preservation, achieves 75.18% average accuracy (peak 81.82%) in 5-fold cross-validation for preterm brain injury prediction.
citing papers explorer
-
Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classification
ARF-SFR-Net adaptively sizes receptive fields in spatial and frequency branches and reconstructs query features from support features, reporting state-of-the-art few-shot fine-grained accuracy on five benchmarks.
-
GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction
GloResNet, a ResNet-10-based lightweight 3D CNN pretrained on MedicalNet with global manifold mapping for topology preservation, achieves 75.18% average accuracy (peak 81.82%) in 5-fold cross-validation for preterm brain injury prediction.