Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification

• URL: http://arxiv.org/abs/2608.15731v1
• Date: Sun, 16 Aug 2026 13:13:22 GMT
• Title: Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification
• Abstract summary: Concept-based Explainable AI ( CXAI) methods need to be assessed for their applicability and problem-solving capacity.<n>We apply two CXAI methods to generate concept-level explanations and investigate the overall evaluations.<n>Our results demonstrate the potential of CXAI to enhance the understanding of model generalizability and to diagnose bias instigated by the dataset.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandable to ensure user trust. In real-world computer vision tasks, these models often operate on complex images containing background noise and are heavily annotated. To make such models explainable, Concept-based Explainable AI (CXAI) methods need to be assessed for their applicability and problem-solving capacity. In this work, we explore CXAI use cases in multi-label classification by training two DNNs, VGG16 and ResNet50, on the 20 most annotated labels in the MS-COCO dataset (Microsoft Common Objects in Context). We apply two CXAI methods, CRP (Concept Relevance Propagation) and CRAFT (Concept Recursive Activation FacTorization), to generate concept-level explanations and investigate the overall evaluations. Our analysis reveals three key findings: (1) CXAI highlights learning weaknesses in DNNs, (2) higher concept distinctiveness reduces label and concept confusion, and (3) environmental concepts expose dataset-induced biases. Our results demonstrate the potential of CXAI to enhance the understanding of model generalizability and to diagnose bias instigated by the dataset.

Related papers

• SCAN: Visual Explanations with Self-Confidence and Analysis Networks [0.764671395172401]
  Self-Confidence and Analysis Networks (SCAN) is a novel universal framework that overcomes limitations for both convolutional neural network and transformer architectures.<n>SCAN consistently achieves outstanding performance on various quantitative metrics such as AUC-D, Negative AUC, Drop%, and Win%.<n>It produces significantly clearer, object-focused explanations than existing methods.
  arXiv  Detail & Related papers  (2026-03-04T17:17:40Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Concept-Guided Interpretability via Neural Chunking [64.6429903327095]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract recurring chunks on a neural population level.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations [13.60538902487872]
  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. We demonstrate the effectiveness of our approach in identifying out-of-distribution samples, spurious model behavior and data quality issues across three datasets.
  arXiv  Detail & Related papers  (2023-11-28T10:53:26Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Explain Any Concept: Segment Anything Meets Concept-Based Explanation [11.433807960637685]
  Segment Anything Model (SAM) has been demonstrated as a powerful framework for performing precise and comprehensive instance segmentation. We offer an effective and flexible concept-based explanation method, namely Explain Any Concept (EAC) We thus propose a lightweight per-input equivalent (PIE) scheme, enabling efficient explanation with a surrogate model.
  arXiv  Detail & Related papers  (2023-05-17T15:26:51Z)
• Neural Causal Models for Counterfactual Identification and Estimation [62.30444687707919]
  We study the evaluation of counterfactual statements through neural models. First, we show that neural causal models (NCMs) are expressive enough. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions.
  arXiv  Detail & Related papers  (2022-09-30T18:29:09Z)
• Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks [4.153804257347222]
  We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100.
  arXiv  Detail & Related papers  (2022-03-07T10:56:13Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction [158.88345945211185]
  We present a novel approach that advances the state of the art on pixel-level prediction in a fundamental aspect, i.e. structured multi-scale features learning and fusion. We propose a probabilistic graph attention network structure based on a novel Attention-Gated Conditional Random Fields (AG-CRFs) model for learning and fusing multi-scale representations in a principled manner.
  arXiv  Detail & Related papers  (2021-01-08T04:14:29Z)
• Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI [12.680653816836541]
  We propose a ground truth based evaluation framework for XAI methods based on the CLEVR visual question answering task. Our framework provides a (1) selective, (2) controlled and (3) realistic testbed for the evaluation of neural network explanations.
  arXiv  Detail & Related papers  (2020-03-16T14:43:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.