Tighnari v2: Mitigating Label Noise and Distribution Shift in Multimodal Plant Distribution Prediction via Mixture of Experts and Weakly Supervised Learning

Ähnliche Einträge

• Weak to Strong: VLM-Based Pseudo-Labeling as a Weakly Supervised Training Strategy in Multimodal Video-based Hidden Emotion Understanding Tasks
  von: Wang, Yufei, et al.
  Veröffentlicht: (2026)
• Tighnari: Multi-modal Plant Species Prediction Based on Hierarchical Cross-Attention Using Graph-Based and Vision Backbone-Extracted Features
  von: Liu, Haixu, et al.
  Veröffentlicht: (2025)
• Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
  von: Zhang, Haojie, et al.
  Veröffentlicht: (2023)
• Instance-dependent Label Distribution Estimation for Learning with Label Noise
  von: Liao, Zehui, et al.
  Veröffentlicht: (2022)
• Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts
  von: He, Xin, et al.
  Veröffentlicht: (2025)