ScholarGate
Asisten
Machine learningDeep learning / NLP / CV

Vision Transformer yang Dapat Dijelaskan

Explainable Vision Transformer menggabungkan kinerja pengenalan gambar yang kuat dari Vision Transformers (ViT) dengan teknik atribusi — seperti propagasi relevansi, pelipatan perhatian, atau perhatian berbobot gradien — yang menyoroti wilayah gambar mana yang mendorong setiap prediksi. Pendekatan ini memungkinkan peneliti dan praktisi untuk mengaudit keputusan model dan memenuhi persyaratan transparansi tanpa mengorbankan akurasi.

Buka di MethodMindSegeraVideoSegeraDownload slides

Baca metode selengkapnya

Khusus anggota

Masuk dengan akun gratis untuk membaca bagian ini.

Masuk

Method map

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

Sumber

  1. Chefer, H., Gur, S., & Wolf, L. (2021). Transformer interpretability beyond attention visualization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 782–791. DOI: 10.1109/CVPR46437.2021.00084
  2. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., … Houlsby, N. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations (ICLR). link

Cara menyitasi halaman ini

ScholarGate. (2026, June 3). Explainable Vision Transformer (XViT / ViT with Post-hoc Attribution). ScholarGate. https://scholargate.app/id/deep-learning/explainable-vision-transformer

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

Dirujuk oleh

ScholarGateExplainable Vision Transformer (Explainable Vision Transformer (XViT / ViT with Post-hoc Attribution)). Diakses 2026-06-15 dari https://scholargate.app/id/deep-learning/explainable-vision-transformer · Set data: https://doi.org/10.5281/zenodo.20539026