4 papers
BAT: Better Audio Transformer Guided by Convex Gated Probing
Houtan Ghaffari, Lukas Rauch, Christoph Scholz +1
Probing is widely adopted in computer vision to faithfully evaluate self-supervised learning (SSL) embeddings, as finetuning may misrepresent their inherent quality. In contrast, a…
Unmute the Patch Tokens: Rethinking Probing in Multi-Label Audio Classification
Lukas Rauch, René Heinrich, Houtan Ghaffari +4
Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursuing state-of-the-art on AudioSet. A ke…
Data-Efficient Self-Supervised Algorithms for Fine-Grained Birdsong Analysis
Houtan Ghaffari, Lukas Rauch, Paul Devos
Research in bioacoustics, neuroscience, and linguistics often uses birdsong as a proxy to acquire knowledge across diverse areas. This requires audio models to annotate and parse t…
Comparison of self-supervised in-domain and supervised out-domain transfer learning for bird species recognition
Houtan Ghaffari, Paul Devos
Transferring the weights of a pre-trained model to assist another task has become a crucial part of modern deep learning, particularly in data-scarce scenarios. Pre-training refers…