Beyond Frequency: Seeing Subtle Cues Through the Lens of Spatial Decomposition for Fine-Grained Visual Classification

Documenti analoghi

• Hard to See, Hard to Label: Generative and Symbolic Acquisition for Subtle Visual Phenomena
  di: Prasad, Renjith, et al.
  Pubblicazione: (2026)
• Saccadic Vision for Fine-Grained Visual Classification
  di: Schmidt, Johann, et al.
  Pubblicazione: (2025)
• Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
  di: Zhang, Qizhe, et al.
  Pubblicazione: (2024)
• SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
  di: Zhou, Sashuai, et al.
  Pubblicazione: (2026)
• SASP: Strip-Aware Spatial Perception for Fine-Grained Bird Image Classification
  di: Wang, Zheng
  Pubblicazione: (2025)