PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers

Documenti analoghi

• Two-stage Vision Transformers and Hard Masking offer Robust Object Representations
  di: Aniraj, Ananthu, et al.
  Pubblicazione: (2025)
• DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning
  di: Ienco, Dino, et al.
  Pubblicazione: (2024)
• Metonymy in vision models undermines attention-based interpretability
  di: Aniraj, Ananthu, et al.
  Pubblicazione: (2026)
• Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
  di: Mena, Francisco, et al.
  Pubblicazione: (2025)
• Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labelling
  di: Dantas, Cassio F., et al.
  Pubblicazione: (2024)