FovEx:面向视觉Transformer与卷积神经网络的类人解释方法
FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks
AI总结:
受人类视觉启发提出模型无关的XAI方法FovEx,结合生物扰动与梯度探索生成归因图,在多种架构上实现SOTA性能,且解释图与人类注视模式高度契合。
摘要:
人工智能可解释性(XAI)始终是提升机器学习模型可信度与可理解性的关键方向。当前的视觉解释技术,例如基于梯度或类激活的方法,通常高度依赖特定的模型架构。与之相对,基于扰动的方法虽具备模型无关性,但计算成本高昂,需要执行大量前向传播来完成模型评估。\n本研究提出了Foveation-based Explanations(FovEx,基于中央凹的解释方法)——一种受人类视觉启发的新型XAI方法。FovEx通过迭代生成图像的中央凹渲染图,融合了受生物启发的扰动机制,并将其与基于梯度的视觉探索相结合,以高效定位感兴趣区域。这些区域的选取原则是最大化待解释模型在下游任务上的性能,随后将这些区域整合生成归因图。\n我们在成熟基准上开展了包含定性与定量评估的全面验证。该方法在Transformer模型(5项指标中4项最优)和卷积模型(5项指标中3项最优)上均达到了当前最优性能,展现了其在不同架构间的通用性。此外,我们证实FovEx生成的解释图与人类注视模式具有一致性:相较于RISE,其NSS指标提升14%;相较于GradCAM,其NSS指标提升203%。这一对比进一步印证了FovEx具备缩小人机解释鸿沟的能力。
英文摘要:
Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, such as gradient-based or class-activation-based methods, often exhibit a strong dependence on specific model architectures. Conversely, perturbation-based methods, despite being model-agnostic, are computationally expensive as they require evaluating models on a large number of forward passes. In this work, we introduce Foveation-based Explanations (FovEx), a novel XAI method inspired by human vision. FovEx seamlessly integrates biologically inspired perturbations by iteratively creating foveated renderings of the image and combines them with gradient-based visual explorations to determine locations of interest efficiently. These locations are selected to maximize the performance of the model to be explained with respect to the downstream task and then combined to generate an attribution map. We provide a thorough evaluation with qualitative and quantitative assessments on established benchmarks. Our method achieves state-of-the-art performance on both transformers (on 4 out of 5 metrics) and convolutional models (on 3 out of 5 metrics), demonstrating its versatility among various architectures. Furthermore, we show the alignment between the explanation map produced by FovEx and human gaze patterns (+14\% in NSS compared to RISE, +203\% in NSS compared to GradCAM). This comparison enhances our confidence in FovEx's ability to close the interpretation gap between humans and machines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。