Weight initialization measurably affects quantized CNN accuracy, and a graph hypernetwork finetuned on quantized networks (GHN-QAT) can predict parameters that survive 4-bit and even 2-bit quantization better than random chance.
Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,
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
-
Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization
Weight initialization measurably affects quantized CNN accuracy, and a graph hypernetwork finetuned on quantized networks (GHN-QAT) can predict parameters that survive 4-bit and even 2-bit quantization better than random chance.