ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Forklarlig Billedklassifikation

Forklarlig billedklassifikation kombinerer en deep learning-billedklassifikator — typisk et CNN eller Vision Transformer — med en post-hoc eller intrinsisk fortolkningsmetode såsom Grad-CAM, LIME eller SHAP for at producere visuelle eller kvantitative forklaringer på, hvorfor modellen tildelte en bestemt etiket til et billede. Målet er at gøre klassifikatorens beslutningsproces gennemsigtig, auditerbar og troværdig.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 618-626. DOI: 10.1109/ICCV.2017.74
  2. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why Should I Trust You?: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135-1144. DOI: 10.1145/2939672.2939778

Sådan citerer du denne side

ScholarGate. (2026, June 3). Explainable Image Classification (XAI-augmented CNN/Transformer Classifiers). ScholarGate. https://scholargate.app/da/deep-learning/explainable-image-classification

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Refereret af

ScholarGateExplainable Image Classification (Explainable Image Classification (XAI-augmented CNN/Transformer Classifiers)). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/explainable-image-classification · Datasæt: https://doi.org/10.5281/zenodo.20539026