Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain
arXiv:2305.14979
Abstract
Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the reliability of a decision, i.e., to know simultaneously if a model relies on the relevant features and whether these features are robust to image corruptions. Existing attribution methods aim to provide human-understandable explanations by highlighting important regions in the image domain, but fail to fully characterize a decision process's reliability. To bridge this gap, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain using wavelet transforms. Attribution in the wavelet domain reveals where and on what scales the model focuses, thus enabling us to assess whether a decision is reliable. Our code is accessible here: \url{https://github.com/gabrielkasmi/spectral-attribution}.
18 pages, 10 figures, 3 tables. Camera-ready version accepted at the XAI in action workshop at NeurIPS 2023
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Fast is better than free: Revisiting adversarial training
- Measuring the tendency of CNNs to Learn Surface Statistical Regularities
- No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
- White Paper Machine Learning in Certified Systems
- ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification
- Rethinking Natural Adversarial Examples for Classification Models
- Spectral Bias in Practice: The Role of Function Frequency in Generalization
- Identifying Spurious Correlations and Correcting them with an Explanation-based Learning