重新思考解释：深度视觉分类器的输入无关显著性映射
Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers
AI总结：
提出输入无关显著性映射新视角，通过累积模型梯度信息计算高级特征并转化为可解释可视化，不仅为大规模模型提供独立定性解释，还能识别受损分类器中的后门签名。
摘要：
显著性方法通过将输入特征归因于模型输出，提供事后模型解释。当前方法主要使用单个输入样本实现这一点，从而无法回答关于模型的输入无关查询。我们还表明，输入特定的显著性映射本质上容易受到误导性特征归因的影响。当前使用“通用”输入特征进行模型解释的尝试假设可以访问包含这些特征的数据集，这会使解释产生偏差。为了解决这一差距，我们引入了输入无关显著性映射的新视角，该视角通过计算估计模型归因于其输出的高级特征。这些特征在几何上是相关的，并且是通过累积模型相对于无限制数据分布的梯度信息来计算的。为了计算这些特征，我们将独立数据点在模型损失表面上推向与人类可理解概念（例如分类器的类标签）相关的局部最小值。通过系统的投影、缩放和细化过程，这些信息被转换为可解释的可视化，而不会损害其模型保真度。该可视化作为独立的定性解释。通过广泛的评估，我们不仅展示了对大规模模型各种概念的成功可视化，而且还通过识别受损分类器中的后门签名，展示了这种新形式显著性映射的有趣效用。
英文摘要：
Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the model. We also show that input-specific saliency mapping is intrinsically susceptible to misleading feature attribution. Current attempts to use 'general' input features for model interpretation assume access to a dataset containing those features, which biases the interpretation. Addressing the gap, we introduce a new perspective of input-agnostic saliency mapping that computationally estimates the high-level features attributed by the model to its outputs. These features are geometrically correlated, and are computed by accumulating model's gradient information with respect to an unrestricted data distribution. To compute these features, we nudge independent data points over the model loss surface towards the local minima associated by a human-understandable concept, e.g., class label for classifiers. With a systematic projection, scaling and refinement process, this information is transformed into an interpretable visualization without compromising its model-fidelity. The visualization serves as a stand-alone qualitative interpretation. With an extensive evaluation, we not only demonstrate successful visualizations for a variety of concepts for large-scale models, but also showcase an interesting utility of this new form of saliency mapping by identifying backdoor signatures in compromised classifiers.
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。
