Do Transformers Understand Ancient Roman Coin Motifs Better than CNNs?

Documenti analoghi

• A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models
  di: Guo, Zhongliang, et al.
  Pubblicazione: (2023)
• This Looks Better than That: Better Interpretable Models with ProtoPNeXt
  di: Willard, Frank, et al.
  Pubblicazione: (2024)
• TraNCE: Transformative Non-linear Concept Explainer for CNNs
  di: Akpudo, Ugochukwu Ejike, et al.
  Pubblicazione: (2025)
• Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
  di: Hatefi, Sayed Mohammad Vakilzadeh, et al.
  Pubblicazione: (2024)
• A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse
  di: Guo, Zhongliang, et al.
  Pubblicazione: (2024)