Concepts from Representations: Post-hoc Concept Bottleneck Models via Sparse Decomposition of Visual Representations

Documenti analoghi

• Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models
  di: Gong, Shizhan, et al.
  Pubblicazione: (2025)
• Interpretable Generative Models through Post-hoc Concept Bottlenecks
  di: Kulkarni, Akshay, et al.
  Pubblicazione: (2025)
• Flexible Concept Bottleneck Model
  di: Du, Xingbo, et al.
  Pubblicazione: (2025)
• Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training
  di: Gong, Shizhan, et al.
  Pubblicazione: (2024)
• In-hoc Concept Representations to Regularise Deep Learning in Medical Imaging
  di: Corbetta, Valentina, et al.
  Pubblicazione: (2025)