Metraipolis › archive › dc_28711bcc3dfc

ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution — arXiv:2610.04605

Source
arXiv
Original
https://arxiv.org/abs/2610.04605
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:20.859Z
SHA-256 of the archived text
7f27426b0a06bea0a5ec7986d97fedab50277e0af576bce3b7ced87bffe737cc
Stable URL of this page
https://metraipolis.com/documento/dc_28711bcc3dfc

How to cite

ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution — arXiv:2610.04605 — arXiv, https://arxiv.org/abs/2610.04605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28711bcc3dfc (Metraipolis archive dc_28711bcc3dfc, sha256 7f27426b0a06bea0a5ec7986d97fedab50277e0af576bce3b7ced87bffe737cc)
BibTeX
@misc{dc28711bcc3dfc,
  title = {ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution — arXiv:2610.04605},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04605},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28711bcc3dfc; sha256 7f27426b0a06bea0a5ec7986d97fedab50277e0af576bce3b7ced87bffe737cc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and trustworthiness. We introduce Concept-based Explanations (ConEx), a novel framework that bridges saliency visualization with concept-based reasoning to provide both faithfulness and interpretability. ConEx automatically discovers class-specific concepts and represents them through concept activation vectors (CAVs), learned without manual supervision using an architecture-specific masking mechanism that reduces noise introduced by the segmentation masks to enhance concept purity. ConEx generates faithful saliency maps that reveal where each concept appears in the image and how it contributes to the prediction. To evaluate the reliability of these learned concepts, we propose two complementary metrics, Vector-Concept Match (VCM) and Concept-Class Match (CCM), that quantify concept alignment and enable direct comparison with existing methods. Extensive experiments across diverse settings demonstrate that ConEx achieves state-of-the-art performance on faithfulness, segmentation, and concept-quality benchmarks. Overall, ConEx advances the field toward truly interpretable and concept-grounded explanations in vision models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04605 — 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 2026-10-06T05:24:05.889Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).