6.8 KiB
Data2Vec
Overview
The Data2Vec model was proposed in data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language by Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu and Michael Auli. Data2Vec proposes a unified framework for self-supervised learning across different data modalities - text, audio and images. Importantly, predicted targets for pre-training are contextualized latent representations of the inputs, rather than modality-specific, context-independent targets.
The abstract from the paper is the following:
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 selfdistillation 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. Models and code are available at www.github.com/pytorch/fairseq/tree/master/examples/data2vec.
This model was contributed by edugp and patrickvonplaten. sayakpaul and Rocketknight1 contributed Data2Vec for vision in TensorFlow.
The original code (for NLP and Speech) can be found here. The original code for vision can be found here.
Usage tips
- Data2VecAudio, Data2VecText, and Data2VecVision have all been trained using the same self-supervised learning method.
- For Data2VecAudio, preprocessing is identical to [
Wav2Vec2Model], including feature extraction - For Data2VecText, preprocessing is identical to [
RobertaModel], including tokenization. - For Data2VecVision, preprocessing is identical to [
BeitModel], including feature extraction.
Resources
A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with Data2Vec.
- [
Data2VecVisionForImageClassification] is supported by this example script and notebook. - To fine-tune [
TFData2VecVisionForImageClassification] on a custom dataset, see this notebook.
Data2VecText documentation resources
- Text classification task guide
- Token classification task guide
- Question answering task guide
- Causal language modeling task guide
- Masked language modeling task guide
- Multiple choice task guide
Data2VecAudio documentation resources
Data2VecVision documentation resources
If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.
Data2VecTextConfig
autodoc Data2VecTextConfig
Data2VecAudioConfig
autodoc Data2VecAudioConfig
Data2VecVisionConfig
autodoc Data2VecVisionConfig
Data2VecAudioModel
autodoc Data2VecAudioModel - forward
Data2VecAudioForAudioFrameClassification
autodoc Data2VecAudioForAudioFrameClassification - forward
Data2VecAudioForCTC
autodoc Data2VecAudioForCTC - forward
Data2VecAudioForSequenceClassification
autodoc Data2VecAudioForSequenceClassification - forward
Data2VecAudioForXVector
autodoc Data2VecAudioForXVector - forward
Data2VecTextModel
autodoc Data2VecTextModel - forward
Data2VecTextForCausalLM
autodoc Data2VecTextForCausalLM - forward
Data2VecTextForMaskedLM
autodoc Data2VecTextForMaskedLM - forward
Data2VecTextForSequenceClassification
autodoc Data2VecTextForSequenceClassification - forward
Data2VecTextForMultipleChoice
autodoc Data2VecTextForMultipleChoice - forward
Data2VecTextForTokenClassification
autodoc Data2VecTextForTokenClassification - forward
Data2VecTextForQuestionAnswering
autodoc Data2VecTextForQuestionAnswering - forward
Data2VecVisionModel
autodoc Data2VecVisionModel - forward
Data2VecVisionForImageClassification
autodoc Data2VecVisionForImageClassification - forward
Data2VecVisionForSemanticSegmentation
autodoc Data2VecVisionForSemanticSegmentation - forward
TFData2VecVisionModel
autodoc TFData2VecVisionModel - call
TFData2VecVisionForImageClassification
autodoc TFData2VecVisionForImageClassification - call
TFData2VecVisionForSemanticSegmentation
autodoc TFData2VecVisionForSemanticSegmentation - call