Self-supervised data2vec backbone
According to the card, the same data2vec learning method spans speech, language, and vision by predicting latent representations of full inputs.
Open Source Model Profile · facebook
data2vec-vision-base-ft1k
data2vec-vision-base-ft1k is a base data2vec vision classifier from facebook. According to the model card, it is fine-tuned on ImageNet-1k at 224x224.
- Publisher
- Task
- image-classification
- Model type
- data2vec-vision
- License
- apache-2.0
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
data2vec-vision-base-ft1k is published by facebook as an image-classification model. The captured configuration identifies Data2VecVisionForImageClassification with model type data2vec-vision. According to the model card, it applies the data2vec self-supervised framework to vision and is fine-tuned on ImageNet-1k at 224x224 resolution.
Recorded capabilities
ImageNet-1k fine-tune at 224
According to the card, the base model was fine-tuned on ImageNet-1k at 224x224 resolution with documented RGB normalization.
Documented Transformers recipe
According to the card, inference uses BeitFeatureExtractor with Data2VecVisionForImageClassification over 1,000 ImageNet classes.
Use cases in the source record
- Image classification into 1,000 ImageNet classes at 224x224 resolution through the documented Transformers recipe.
- Representation-reuse experiments starting from the ImageNet-1k fine-tuned vision backbone.
Limitations and unknowns
- No parameter count was extracted from this record.
- No evaluation scores were extracted; the card defers evaluation to Table 1 of the original paper.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: facebook/data2vec-vision-base-ft1k
Captured: Unknown. Processed: 2026-09-07T19:34:44.350683+00:00.
Data2Vec-Vision (base-sized model, fine-tuned on ImageNet-1k) BEiT model pre-trained in a self-supervised fashion and fine-tuned on ImageNet-1k (1,2 million images, 1000 classes) at resolution 224x224. It was introduced in the paper 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, Michael Auli and first released in this repository . Disclaimer: The team releasing Facebook team did not write a model card for this model so this model card has been written by the Hugging Face team. Pre-Training method For more information, pleas…
F001F002F003F004F005F006F009F010F013F014F015F017F018