Saliency maps that identify the most informative regions of an image for a classifier are valuable for model interpretability. A common approach to creating saliency maps involves generating input masks that mask out portions of an image to maximally deteriorate classification performance, or mask in an image to preserve classification performance. Many variants of this approach have been proposed in the literature, such as counterfactual generation and optimizing over a Gumbel-Softmax distribution. Using a general formulation of masking-based saliency methods, we conduct an extensive evaluation study of a number of recently proposed variants to understand which elements of these methods meaningfully improve performance. Surprisingly, we find that a well-tuned, relatively simple formulation of a masking-based saliency model outperforms many more complex approaches. We find that the most important ingredients for high quality saliency map generation are (1) using both masked-in and masked-out objectives and (2) training the classifier alongside the masking model. Strikingly, we show that a masking model can be trained with as few as 10 examples per class and still generate saliency maps with only a 0.7-point increase in localization error.
Adversarial examples provoke weak reliability and potential security issues in deep neural networks. Although adversarial training has been widely studied to improve adversarial robustness, it works in an over-parameterized regime and requires high computations and large memory budgets. To bridge adversarial robustness and model compression, we propose a novel adversarial pruning method, Masking Adversarial Damage (MAD) that employs second-order information of adversarial loss. By using it, we can accurately estimate adversarial saliency for model parameters and determine which parameters can …
Opti-CAM: Optimizing saliency maps for interpretability
Centrale Marseille（马赛中央理工学院）；Aix Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；LIS（信息科学实验室）；Institute of Advanced Research on Artificial Intelligence (IARAI)（人工智能高级研究院（IARAI））
In this study, we propose a novel method to measure bottom-up saliency maps of natural images. In order to eliminate the influence of top-down signals, backward masking is used to make stimuli (natural images) subjectively invisible to subjects, however, the bottom-up saliency can still orient the subjects attention. To measure this orientation/attention effect, we adopt the cueing effect paradigm by deploying discrimination tasks at each location of an image, and measure the discrimination performance variation across the image as the attentional effect of the bottom-up saliency. Such attenti…
The black-box nature of the deep networks makes the explanation for "why" they make certain predictions extremely challenging. Saliency maps are one of the most widely-used local explanation tools to alleviate this problem. One of the primary approaches for generating saliency maps is by optimizing a mask over the input dimensions so that the output of the network is influenced the most by the masking. However, prior work only studies such influence by removing evidence from the input. In this paper, we present iGOS++, a framework to generate saliency maps that are optimized for altering the o…
SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote Sensing
School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Artificial Intelligence and Automation, Wuhan University of Science and Technology（武汉科技大学人工智能与自动化学院）；School of Electronic Information, Wuhan University of Science and Technology（武汉科技大学电子信息学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）
Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly limited owing to their poor scalability with larger networks. In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model explanation. In particular, we apply this technique to identify minimal regions in an input that are most relevant for a neural network's prediction. Our approach uses gradient information (based …
