2 papers
cs.LG2025
Saliency Maps are Ambiguous: Analysis of Logical Relations on First and Second Order Attributions
Leonid Schwenke, Martin Atzmueller
Recent work uncovered potential flaws in \eg attribution or heatmap based saliency methods. A typical flaw is a confirmations bias, where the scores are compared to human expectati…
cs.LG2024
Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretation
Leonid Schwenke, Martin Atzmueller
With their increase in performance, neural network architectures also become more complex, necessitating explainability. Therefore, many new and improved methods are currently emer…