# How a Model's Architecture and Performance Influences Explainability: A Study of Grad-CAM and CRAFT in CNN-Based Image Classification

DevFeed: [How a Model's Architecture and Performance Influences Explainability: A Study of Grad-CAM and CRAFT in CNN-Based Image Classification](<https://devfeed.tech/articles/how-a-model-s-architecture-and-performance-influences-explainability-a-study-of-grad-cam-and-craft-in-cnn-based-image-classification-126225.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12075>)

Author: Kilian G\\"oller, Haadia Amjad, Steffen Seitz, Carsten Knoll, Ronald Tetzlaff

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>)

Tags: [accountability](<https://devfeed.tech/tags/accountability.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-systems](<https://devfeed.tech/tags/autonomous-systems.md>), [classes](<https://devfeed.tech/tags/classes.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cnn](<https://devfeed.tech/tags/cnn.md>), [cnns](<https://devfeed.tech/tags/cnns.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [craft](<https://devfeed.tech/tags/craft.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [explainability](<https://devfeed.tech/tags/explainability.md>), [image](<https://devfeed.tech/tags/image.md>), [image-classification](<https://devfeed.tech/tags/image-classification.md>), [model](<https://devfeed.tech/tags/model.md>), [performance](<https://devfeed.tech/tags/performance.md>), [study](<https://devfeed.tech/tags/study.md>)

## AI overview

The study finds that explanation quality varies with both CNN architecture and training progress. Across 10 ImageNet-1K subsets, it evaluates VGG16, ResNet50, and ConvNeXt-Tiny at 10 accuracy checkpoints using Grad-CAM and CRAFT, measuring Faithfulness, Correctness, Sensitivity, and Simplicity. As training progresses, ResNet50 and ConvNeXt-Tiny show improved Faithfulness and lower Sensitivity. VGG16 produces simpler explanations, but they are less faithful and correct. The supplied abstract does not report method-specific results distinguishing Grad-CAM from CRAFT.

## Source excerpt

arXiv:2611.12075v1 Announce Type: cross Abstract: Deep learning models, particularly convolutional neural networks (CNNs), are widely adopted in computer vision, yet their opaque decision-making raises concerns in high-risk applications like healthcare and autonomous systems, where trust and accountability are critical. Therefore, robust explainable AI (XAI) methods are desirable to provide transparent insights into model decisions. To ensure these methods are reliable and effective across diverse scenarios, it is important to understand how model performance and architectural complexity influence explanation quality. Our study takes an initial step toward systematically investigating the impact of these two factors on key XAI evaluation metrics. We constructed a pipeline using 10 subsets of ImageNet-1K, each containing 80 unique classes, on each of which we trained three CNN architectures of increasing structural complexity: VGG16, ResNet50, and ConvNeXt-Tiny. For each individual model, we analyzed 10 training checkpoints representing increasing levels of model accuracy using two XAI methods: Grad-CAM (feature-attribution-based) and CRAFT (concept-based). We assessed these methods across four evaluation categories: Faithfulness, Correctness, Sensitivity, and Simplicity. Our findings reveal that as training progresses, the complex architectures (ResNet50 and ConvNeXt-Tiny) exhibit improved Faithfulness and lower Sensitivity, indicating more robust explanations. In contrast, VGG16's simpler architecture yields simpler but less faithful and correct explanations.