A Spitting Image: Modular Superpixel Tokenization in Vision Transformers

Documenti analoghi

• Differentiable Hierarchical Visual Tokenization
  di: Aasan, Marius, et al.
  Pubblicazione: (2025)
• Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
  di: Li, Jinhao, et al.
  Pubblicazione: (2024)
• Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors
  di: Zhang, Junbin, et al.
  Pubblicazione: (2026)
• Non-Robust Features are Not Always Useful in One-Class Classification
  di: Lau, Matthew, et al.
  Pubblicazione: (2024)
• Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing
  di: Komurcu, Kursat, et al.
  Pubblicazione: (2026)