相关论文: Sanity checks for patch visualisation in prototype…

Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making increases cognitive complexity and hinders user understanding.…

As data-driven intelligent systems advance, the need for reliable and transparent decision-making mechanisms has become increasingly important. Therefore, it is essential to integrate uncertainty quantification and model explainability…

In this work, we introduce InfoDisent, a hybrid approach to explainability based on the information bottleneck principle. InfoDisent enables the disentanglement of information in the final layer of any pretrained model into atomic concepts,…

Visualization and topic modeling are widely used approaches for text analysis. Traditional visualization methods find low-dimensional representations of documents in the visualization space (typically 2D or 3D) that can be displayed using a…

We introduce a new tool for interpreting neural net responses, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed representation which…

Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to…

In Zero-Shot Learning (ZSL), embedding-based methods enable knowledge transfer from seen to unseen classes by learning a visual-semantic mapping from seen-class images to class-level semantic prototypes (e.g., attributes). However, these…

Automatic metrics are now central to evaluating text-to-image models, often substituting for human judgment in benchmarking and large-scale filtering. However, it remains unclear whether these metrics truly prioritize semantic correctness…

We present an interpretable neural network approach to predicting and understanding politeness in natural language requests. Our models are based on simple convolutional neural networks directly on raw text, avoiding any manual…

Prototypical parts networks combine the power of deep learning with the explainability of case-based reasoning to make accurate, interpretable decisions. They follow the this looks like that reasoning, representing each prototypical part…

Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, we propose an…

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…

Although many tools have been presented in the research literature of software visualization, there is little evidence of their adoption. To choose a suitable visualization tool, practitioners need to analyze various characteristics of…

Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization. Yet a broadly applicable, quantitative measure of simplicity remains elusive. We introduce…

Background and Objective: Prototype-based methods improve interpretability by learning fine-grained part-prototypes; however, their visualization in the input pixel space is not always consistent with human-understandable biomarkers. In…

Recently, data-driven deep saliency models have achieved high performance and have outperformed classical saliency models, as demonstrated by results on datasets such as the MIT300 and SALICON. Yet, there remains a large gap between the…

Visual storytelling aims to generate compelling narratives from image sequences. Existing models often focus on enhancing the representation of the image sequence, e.g., with external knowledge sources or advanced graph structures. Despite…

We present a new approach for a single view, image-based object pose estimation. Specifically, the problem of culling false positives among several pose proposal estimates is addressed in this paper. Our proposed approach targets the…

Saliency maps can explain a neural model's predictions by identifying important input features. They are difficult to interpret for laypeople, especially for instances with many features. In order to make them more accessible, we formalize…

This study proposes a retinal prosthetic simulation framework driven by visual fixations, inspired by the saccade mechanism, and assesses performance improvements through end-to-end optimization in a classification task. Salient patches are…