AI RESEARCH
BAT: Better Audio Transformer Guided by Convex Gated Probing
arXiv CS.LG
•
ArXi:2602.16305v2 Announce Type: replace-cross Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as finetuning may misrepresent their inherent quality. In contrast, audio SSL models still rely on finetuning because simple probing fails to unlock their full potential and alters their rankings when competing on AudioSet. Hence, a robust and efficient probing mechanism is required to guide the trajectory of audio SSL towards reliable and reproducible methods. We