3 papers
cs.SD2025
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…
cs.CV2024
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter +1
We introduce MIM (Masked Image Modeling)-Refiner, a contrastive learning boost for pre-trained MIM models. MIM-Refiner is motivated by the insight that strong representations withi…
cs.CV2023
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
Johannes Lehner, Benedikt Alkin, Andreas Fürst +3
Masked Image Modeling (MIM) methods, like Masked Autoencoders (MAE), efficiently learn a rich representation of the input. However, for adapting to downstream tasks, they require a…