Metraipolis › archive › dc_04bbbdc13d5f

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification — arXiv:2608.15731

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15731
License (as archived)
CC0-1.0
Archived
2026-10-18T18:04:22.189Z
SHA-256 of the archived text
042d2b011d5ee518c1f0ad4ec0625f623621fe99b7ad789b9f30059871edd9ac
Stable URL of this page
https://metraipolis.com/documento/dc_04bbbdc13d5f

How to cite

Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification — arXiv:2608.15731 — arXiv (en), https://arxiv.org/abs/2608.15731 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_04bbbdc13d5f (Metraipolis archive dc_04bbbdc13d5f, sha256 042d2b011d5ee518c1f0ad4ec0625f623621fe99b7ad789b9f30059871edd9ac)
BibTeX
@misc{dc04bbbdc13d5f,
  title = {Identifying Confusion Trends in Concept-based XAI for Multi-Label Classification — arXiv:2608.15731},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15731},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_04bbbdc13d5f; sha256 042d2b011d5ee518c1f0ad4ec0625f623621fe99b7ad789b9f30059871edd9ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15731. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15731 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:14.047Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).