Related papers: Sanity checks for patch visualisation in prototype…

Neural networks are commonly regarded as black boxes performing incomprehensible functions. For classification problems networks provide maps from high dimensional feature space to K-dimensional image space. Images of training vector are…

Evaluating explanations of image classifiers regarding ground truth, e.g. segmentation masks defined by human perception, primarily evaluates the quality of the models under consideration rather than the explanation methods themselves.…

We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object detection systems in…

This work analyses the impact of self-supervised pre-training on document images in the context of document image classification. While previous approaches explore the effect of self-supervision on natural images, we show that patch-based…

As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM…

Prototyping is widely regarded in Human-Computer Interaction as an iterative process through which ideas are tested and refined, often via visual mockups, screen flows, and coded simulations. This position paper critiques the visual-centric…

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the…

This paper is a study of techniques for measuring and predicting visual fidelity. As visual stimuli we use polygonal models, and vary their fidelity with two different model simplification algorithms. We also group the stimuli into two…

In this paper we address the problem of unsupervised localization of objects in single images. Compared to previous state-of-the-art method our method is fully unsupervised in the sense that there is no prior instance level or category…

Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions. Still, the usability of existing methods is limited to image classification models. To overcome this…

Visual validation of regression models in scatterplots is a common practice for assessing model quality, yet its efficacy remains unquantified. We conducted two empirical experiments to investigate individuals' ability to visually validate…

Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks,…

Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition. However, a resulting…

In this paper, we propose a data-free method of extracting Impressions of each class from the classifier's memory. The Deep Learning regime empowers classifiers to extract distinct patterns (or features) of a given class from training data,…

We consider the problem of visually explaining similarity models, i.e., explaining why a model predicts two images to be similar in addition to producing a scalar score. While much recent work in visual model interpretability has focused on…

As machine learning (ML) models and datasets increase in complexity, the demand for methods that enhance explainability and interpretability becomes paramount. Prototypes, by encapsulating essential characteristics within data, offer…

We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by making…

Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool…

The analysis of complex high-dimensional data is a common task in many domains, resulting in bespoke visual exploration tools. Expectations and practices of domain experts as users do not always align with visualization theory. In this…

Creating Computer Vision (CV) models remains a complex practice, despite their ubiquity. Access to data, the requirement for ML expertise, and model opacity are just a few points of complexity that limit the ability of end-users to build,…