The FLAVA model was proposed in FLAVA: A Foundational Language And Vision Alignment Model by Amanpreet Singh, Ronghang Hu, Vedanuj Goswami, Guillaume Couairon, Wojciech Galuba, Marcus Rohrbach, and Douwe Kiela and is accepted at CVPR 2022.
The paper aims at creating a single unified foundation model which can work across vision, language as well as vision-and-language multimodal tasks.
The abstract from the paper is the following:
State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.
This model was contributed by aps.
[[autodoc]] FLAVAConfig - from_configs
[[autodoc]] FLAVATextConfig
[[autodoc]] FLAVAImageConfig
[[autodoc]] FLAVAMultimodalConfig
[[autodoc]] FLAVACodebookConfig
[[autodoc]] FLAVAForPretraining - forward
[[autodoc]] FLAVAModel - forward - get_text_features - get_image_features
[[autodoc]] FLAVACodebook - forward - get_codebook_indices - get_codebook_probs
[[autodoc]] FLAVATextModel - forward
[[autodoc]] FLAVAImageModel - forward
[[autodoc]] FLAVAMultimodalModel - forward