As shown in Figure 13, we applied higher noise settings (SNR 0.005, 0.001) to the

As shown in Figure 13, we applied higher noise settings (SNR 0.005, 0.001) to the

Abstract--Even foundational models that are trained on datasets with billions of data samples may develop shortcuts that lead to overfitting and bias. Shortcuts are non-relevant patterns in data, such as the background color or color intensity. So, to ensure the robustness of deep learning applications, there is a need for methods to detect and remove such shortcuts. Today's model debugging methods are time consuming since they often require customization to fit for a given model architecture in a specific domain. We propose a generalized, model-agnostic framework to debug deep learning models. We focus on the domain of histopathology, which has very large images that require large models - and therefore large computation resources. It can be run on a workstation with a commodity GPU. We demonstrate that our framework can replicate non-image shortcuts that have been found in previous work for self-supervised learning models, and we also identify possible shortcuts in a foundation model. Our easy to use tests contribute to the development of more reliable, accurate, and generalizable models for WSI analysis. Pathologists examining tissue specimens mounted on glass slides using a high-powered microscope is the gold standard for cancer diagnosis. Currently, glass slides are digitized into whole-slide images (WSI) that comprise billions of pixels and millions of cells. However, it is difficult for humans to extract all relevant features for prognosis in the plethora of information available in a WSI. Deep learning (DL) models therefore show great promise for WSI analysis both by themselves and as decision support for pathologists. For example, DL has demonstrated its usefulness for cancer type classification [3][9], tissue segmentation [19] and analysis of tissue microenvironments [39][41].

Stacking (or stacked generalization) is an ensemble learning method with one main distinctiveness from the rest: even though several base models are trained on the original data set, their predictions are further used as input data for one or more metamodels arranged in at least one extra layer. Composing a stack of models can produce high-performance outcomes, but it usually involves a trial-and-error process. Therefore, our previously developed visual analytics system, StackGenVis, was mainly designed to assist users in choosing a set of top-performing and diverse models by measuring their predictive performance. However, it only employs a single logistic regression metamodel. In this paper, we investigate the impact of alternative metamodels on the performance of stacking ensembles using a novel visualization tool, called MetaStackVis. Our interactive tool helps users to visually explore different singular and pairs of metamodels according to their predictive probabilities and multiple validation metrics, as well as their ability to predict specific problematic data instances. MetaStackVis was evaluated with a usage scenario based on a medical data set and via expert interviews.