CARE: שיפור תשומת הלב המוגבלת להכרה ויזואלית דקה באמצעות חידוש תלמיד-מורה

תקציר מקורי באנגליתarXiv:2610.11153v1 Announce Type: cross Abstract: Fine-grained visual classification requires models to recognize subtle local traits while exposing the visual evidence behind their predictions. Class-specific attention pathways provide a natural basis for interpretable recognition, but their constrained prediction structure limits discriminative capacity and underuses intermediate representations from strong pretrained backbones. To address this problem, we propose CARE, a constrained attention refinement framework for interpretable fine-grained recognition via teacher-student distillation. CARE keeps the final prediction and explanation within a class-specific attention student, while introducing a training-only auxiliary query teacher that reads selected intermediate DINOv2 layers with