כתבה
arXiv cs.AI ·
FM-ReID: רוטינג טוקן תחרותי סלקטיבי לזיהוי מחדש של עצמים
FM-ReID: Selective Competitive Token Routing for Object Re-Identification
פרקטיקה לזיהוי מחדש של עצמים המשתמשת ברוטינג טוקן תחרותי סלקטיבי.
תקציר מקורי באנגליתarXiv:2609.36560v1 Announce Type: cross Abstract: Object re-identification (ReID) faces a recurring challenge: different identities can share highly similar global appearances, while the cues that distinguish them are localized, heterogeneous, and visible only under particular viewpoints. This challenge arises in animal ReID through markings, contours, and scars, in person ReID through subtle clothing and accessory cues, and in vehicle ReID through localized appearance details. Although visual foundation models encode such information in dense tokens, a single holistic descriptor can obscure discriminative local signals. We propose FM-ReID, an end-to-end framework that formulates local representation learning as selective competitive token routing. Its Competitive Fine-grained Mining modul
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית