Get started
Work

Quantifying and mitigating explanation drift under INT8 quantization in plant disease image classification

Year: 2026
Type: article
Abstract: Deep learning image classifiers are routinely compressed to INT8 for edge deployment, yet the effect of quantization on post-hoc saliency explanations has not been quantified at scale. We define explanation drift as the systematic change in a saliency map between a full-precision (FP32) model and its fake-quantized INT8 simulation, and measure it with three metrics reported against explicit random-overlap baselines: top- k Intersection-over-Union, top- k Dice, and Spearman rank correlation. We evaluate four explanation methods (Grad-CAM, Grad-CAM++, Integrated Gradients, LIME) on three architectures spanning distinct design families (EfficientNetV2-S, ResNet-50, MobileNetV3-Large) fine-tuned on the Paddy Disease Classification dataset (10 classes, 10,407 images), yielding 3,240 paired saliency comparisons per operating point on a stratified 320-image subset of the validation split. A central methodological finding is that the choice of Grad-CAM target layer, not quantization, governs whether attribution appears to survive: for all three architectures the last module returned by a naive “final layer” heuristic emits a $$1\times 1$$ spatial tensor, which forces a constant saliency map and produces spurious attribution collapse in up to $$61.7\%$$ of images. With architecture-appropriate target layers resolved by an explicit spatial-dimension criterion, no collapse occurs in any of the 3,240 comparisons, and drift is substantial but bounded: mean top- k IoU ranges from 0.366 to 0.790 across architecture–method pairs (4.5–9.7 $$\times $$ the random-overlap baseline of 0.081) with median Spearman $$\rho = 0.850$$ . Drift remains strongly method- and architecture-dependent, with Integrated Gradients least preserved and MobileNetV3-Large most affected among architectures. Calibration choice dominates deployment fidelity: on the full validation split, MinMax calibration in ONNX Runtime reduces FP32–INT8 prediction agreement to 0.644 and 0.641 for EfficientNetV2-S and MobileNetV3-Large, whereas percentile calibration restores it to 0.927 and 0.915. Explanation-aware quantization-aware training with a teacher–student CAM consistency loss improves MobileNetV3-Large (top- k IoU $$+16.3\%$$ ) but degrades EfficientNetV2-S ( $$-8.5\%$$ to $$-26.0\%$$ ) relative to post-training quantization; a $$\lambda = 0$$ control isolates the cause, showing that the direction of these changes is present in standard QAT, while the consistency term improves top- k IoU in all nine architecture–method cells relative to that control ( $$+0.6\%$$ to $$+14.4\%$$ , six significant after Holm correction). Stored full-validation CAM summaries differ from the primary subset by at most 1.4 percentage points in IoU; matching per-image records are unavailable, limiting independent verification. Finally, the auxiliary ground-truth localisation summaries (with incompletely verified execution provenance) for annotated SIIM-ACR chest radiographs report low mean FP32 and INT8 overlap with expert masks, illustrating why explanation similarity under quantization must not be read as explanation quality . Analysis code, figure-generation software, and derived result tables are openly archived.
DOI: 10.1038/s41598-026-75299-1
Language: English
Open Access status: gold
Estimated APC paid: $2,690
Funder: Nvidia
OpenAlex ID: W7202044111
FWCI:
Cites:
Cited by:
Related to: