Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input
This work addresses a bottleneck in self-supervised learning for audio and image domains, offering an incremental improvement over existing methods.
The paper tackles the problem of learning representations in self-supervised learning by proposing Masked Modeling Duo (M2D), which directly learns representations using only masked patches, resulting in new state-of-the-art performance on audio tasks like UrbanSound8K and AudioSet20K.
Masked Autoencoders is a simple yet powerful self-supervised learning method. However, it learns representations indirectly by reconstructing masked input patches. Several methods learn representations directly by predicting representations of masked patches; however, we think using all patches to encode training signal representations is suboptimal. We propose a new method, Masked Modeling Duo (M2D), that learns representations directly while obtaining training signals using only masked patches. In the M2D, the online network encodes visible patches and predicts masked patch representations, and the target network, a momentum encoder, encodes masked patches. To better predict target representations, the online network should model the input well, while the target network should also model it well to agree with online predictions. Then the learned representations should better model the input. We validated the M2D by learning general-purpose audio representations, and M2D set new state-of-the-art performance on tasks such as UrbanSound8K, VoxCeleb1, AudioSet20K, GTZAN, and SpeechCommandsV2. We additionally validate the effectiveness of M2D for images using ImageNet-1K in the appendix.