Post-training quantization to 8 or 4 bits preserves accuracy for many CNNs but can silently degrade the similarity of Grad-CAM and LIME explanations to the full-precision model, with DenseNet161 most stable and EfficientNet-B0 least stable.
IEEE Transactions on Neural Networks 6, 1446–1451
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations
Post-training quantization to 8 or 4 bits preserves accuracy for many CNNs but can silently degrade the similarity of Grad-CAM and LIME explanations to the full-precision model, with DenseNet161 most stable and EfficientNet-B0 least stable.