Training quantized models on low-frequency images plus frequency-aware batch normalization at test time improves both compression and domain-shift robustness.
R2snet: Scalable domain adaptation for object detection in cloud– based robotic ecosystems via proposal refinement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Frequency Composition for Compressed and Domain-Adaptive Neural Networks
Training quantized models on low-frequency images plus frequency-aware batch normalization at test time improves both compression and domain-shift robustness.