paper-with-me

Papers

Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations

2023-11-28 · Maximilian Dreyer, Reduan Achtibat, Wojciech Samek, Sebastian Lapuschkin

Ensuring both transparency and safety is critical when deploying Deep Neural Networks (DNNs) in high-risk applications, such as medicine. The field of explainable AI (XAI) has proposed various methods to comprehend the decision-making processes of opaque DNNs. However, only few XAI methods are suitable of ensuring safety in practice as they heavily rely on repeated labor-intensive and possibly biased human assessment. In this work, we present a novel post-hoc concept-based XAI framework that conveys besides instance-wise (local) also class-wise (global) decision-making strategies via prototypes. What sets our approach apart is the combination of local and global strategies, enabling a clearer understanding of the (dis-)similarities in model decisions compared to the expected (prototypical) concept use, ultimately reducing the dependence on human long-term assessment. Quantifying the deviation from prototypical behavior not only allows to associate predictions with specific model sub-strategies but also to detect outlier behavior. As such, our approach constitutes an intuitive and explainable tool for model validation. We demonstrate the effectiveness of our approach in identifying out-of-distribution samples, spurious model behavior and data quality issues across three datasets (ImageNet, CUB-200, and CIFAR-10) utilizing VGG, ResNet, and EfficientNet architectures. Code is available on https://github.com/maxdreyer/pcx.

📄 PDF Abstract BibTeX arXiv:2311.16681

Code (1)

maxdreyer/pcx 공식 구현 pytorch

Tasks

Decision Making

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Batch Normalization 설명 없음
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
Sigmoid Activation 설명 없음

Similar Papers 제목 키워드 기반

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision

2024-05-23 · Mateusz Pach, Dawid Rymarczyk, Koryna Lewandowska, Jacek Tabor 외

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 …

InfoDisent: Explainability of Image Classification Models by Information Disentanglement

2024-09-16 · Łukasz Struski, Jacek Tabor

Understanding the decisions made by image classification networks is a critical area of research in deep learning. This task is traditionally divided into two distinct approaches: post-hoc methods and intrinsic methods. …

ClassificationDisentanglementimage-classificationImage Classification

From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement

2026-04-07 · Cedric Haufe, Frieder Stolzenburg arxiv

We present a neurosymbolic approach, i.e. combine symbolic and subsymbolic artificial intelligence, to validating offer documents in regulated public institutions. We employ a language model to extract information and th…

SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence

2025-07-25 · Viktar Dubovik, Łukasz Struski, Jacek Tabor, Dawid Rymarczyk arxiv

Understanding the decisions made by deep neural networks is essential in high-stakes domains such as medical imaging and autonomous driving. Yet, these models often lack transparency, particularly in computer vision. Pro…

Autonomous Driving

Rethinking Prototypical Contrastive Learning through Alignment, Uniformity and Correlation

2022-10-18 · Shentong Mo, Zhun Sun, Chao Li

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize…

Contrastive LearningDiversitySelf-Supervised Learning