相关论文: SIC: Similarity-Based Interpretable Image Classifi…

The task of remote sensing image scene classification (RSISC), which aims at classifying remote sensing images into groups of semantic categories based on their contents, has taken the important role in a wide range of applications such as…

To tackle increasingly complex tasks, it has become an essential ability of neural networks to learn abstract representations. These task-specific representations and, particularly, the invariances they capture turn neural networks into…

We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by…

Attention mechanisms form a core component of several successful deep learning architectures, and are based on one key idea: ''The output depends only on a small (but unknown) segment of the input.'' In several practical applications like…

The diagnosis of oral diseases presents a problematic clinical challenge, characterized by a wide spectrum of pathologies with overlapping symptomatology. To address this, we developed Clinical Semantic Intelligence (CSI), a novel…

As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on activations, making them dataset-dependent, vulnerable to data…

Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to…

Convolutional neural networks (CNNs) are widely used for high-stakes applications like medicine, often surpassing human performance. However, most explanation methods rely on post-hoc attribution, approximating the decision-making process…

The opportunity to utilize complex functional data types for conducting classification tasks is emerging with the growing availability of imaging data. However, the tools capable of effectively managing imaging data are limited, let alone…

Most classification models treat different object classes in parallel and the misclassifications between any two classes are treated equally. In contrast, human beings can exploit high-level information in making a prediction of an unknown…

How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two…

Explainable artificial intelligence (XAI) aims to develop transparent explanatory approaches for "black-box" deep learning models. However,it remains difficult for existing methods to achieve the trade-off of the three key criteria in…

Combining neural networks with continuous logic and multicriteria decision making tools can reduce the black box nature of neural models. In this study, we show that nilpotent logical systems offer an appropriate mathematical framework for…

Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision…

Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…

The growing reproducibility crisis in machine learning has brought forward a need for careful examination of research findings. This paper investigates the claims made by Lei et al. (2023) regarding their proposed method, LICO, for…

Quantifying the causal influence of input features within neural networks has become a topic of increasing interest. Existing approaches typically assess direct, indirect, and total causal effects. This work treats NNs as structural causal…

Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the desired modification. Despite the rapid development of CIR models, their performance is…

Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…

Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most accurate models often hinders their safe use. Thus, there is a…