Data2vec: A General Framework For Self-supervised Learning In Speech, Vision And Language

Abstract

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised learning, we present data2vec, a framework that uses the same learning method for either speech, NLP or computer vision. The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such as words, visual tokens or units of human speech which are local in nature, data2vec predicts contextualized latent representations that contain information from the entire input. Experiments on the major benchmarks of speech recognition, image classification, and natural language understanding demonstrate a new state of the art or competitive performance to predominant approaches.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybaevski2022data2vec

Related papers

• Av-data2vec: Self-supervised Learning Of Audio-visual Speech Representations With Contextualized Target Representations (2023)0.00
• Token2vec: A Joint Self-supervised Pre-training Framework Using Unpaired Speech And Text (2022)7.16
• Multichannel Av-wav2vec2: A Framework For Learning Multichannel Multi-modal Speech Representation (2024)7.16
• Self-supervised Audio-visual Speech Representations Learning By Multimodal Self-distillation (2022)0.00
• Multi-task Voice Activated Framework Using Self-supervised Learning (2021)6.34
• Wav2vec 2.0: A Framework For Self-supervised Learning Of Speech Representations (2020)0.00
• Emotion2vec: Self-supervised Pre-training For Speech Emotion Representation (2023)15.88
• Speech2vec: A Sequence-to-sequence Framework For Learning Word Embeddings From Speech (2018)14.15