Related papers: Deep Integrated Explanations
Artificial intelligence is reshaping science and industry, yet many users still regard its models as opaque "black boxes". Conventional explainable artificial-intelligence methods clarify individual predictions but overlook the upstream…
In recent years, deep learning models have been extensively applied to biological data across various modalities. Discriminative deep learning models have excelled at classifying images into categories (e.g., healthy versus diseased,…
Explainable AI (XAI) aims to improve user understanding and decisions when using AI models. However, despite innovations in XAI, recent user evaluations reveal that this goal remains elusive. Understanding human cognition can help explain…
Deep neural networks (DNNs) have found their way into many applications with potential impact on the safety, security, and fairness of human-machine-systems. Such require basic understanding and sufficient trust by the users. This motivated…
Deep learning has transformed computer vision (CV), achieving outstanding performance in classification, segmentation, and related tasks. Such AI-based CV systems are becoming prevalent, with applications spanning from medical imaging to…
Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a…
A detailed environment representation is a crucial component of automated vehicles. Using single range sensor scans, data is often too sparse and subject to occlusions. Therefore, we present a method to augment occupancy grid maps from…
Interacting and understanding with text heavy visual content with multiple images is a major challenge for traditional vision models. This paper is on enhancing vision models' capability to comprehend or understand and learn from images…
Limited real-world data severely impacts model performance in many computer vision domains, particularly for samples that are underrepresented in training. Synthetically generated images are a promising solution, but 1) it remains unclear…
With artificial intelligence (AI) embedded in many everyday software systems, effectively and reliably developing and maintaining AI systems becomes an essential skill for software developers. However, the complexity inherent to AI poses…
Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement learning literature has focused on extracting similar…
With Artificial Intelligence (AI) becoming ubiquitous in every application domain, the need for explanations is paramount to enhance transparency and trust among non-technical users. Despite the potential shown by Explainable AI (XAI) for…
Artificial Intelligence techniques powered by deep neural nets have achieved much success in several application domains, most significantly and notably in the Computer Vision applications and Natural Language Processing tasks. Surpassing…
Understanding what deep network models capture in their learned representations is a fundamental challenge in computer vision. We present a new methodology to understanding such vision models, the Visual Concept Connectome (VCC), which…
Recent concept-based interpretable models have succeeded in providing meaningful explanations by pre-defined concept sets. However, the dependency on the pre-defined concepts restricts the application because of the limited number of…
Deep learning models are powerful image classifiers but their opacity hinders their trustworthiness. Explanation methods for capturing the reasoning process within these classifiers faithfully and in a clear manner are scarce, due to their…
Self-supervised learning has made unsupervised pretraining relevant again for difficult computer vision tasks. The most effective self-supervised methods involve prediction tasks based on features extracted from diverse views of the data.…
We introduce a new, systematic framework for visualizing information flow in deep networks. Specifically, given any trained deep convolutional network model and a given test image, our method produces a compact support in the image domain…
Given the complexity and lack of transparency in deep neural networks (DNNs), extensive efforts have been made to make these systems more interpretable or explain their behaviors in accessible terms. Unlike most reviews, which focus on…
We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness. We first developed new gradient-based XAI methods for…