--- license: apache-2.0 tags: - question-answering - visual_bert --- # Model Card for KeywordIdentifier # Model Details ## Model Description VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language (V&L) tasks on image-caption data. - **Developed by:** UCLA NLP - **Shared by [Optional]:** UCLA NLP - **Model type:** Question Answering - **Language(s) (NLP):** More information needed - **License:** Apache 2.0 - **Parent Model:** [XLNet](https://huggingface.co/xlnet-base-cased?text=My+name+is+Mariama%2C+my+favorite) - **Resources for more information:** - [GitHub Repo](https://github.com/uclanlp/visualbert) - [Associated Paper](https://arxiv.org/abs/1908.03557) - [HF hub docs](https://huggingface.co/docs/transformers/model_doc/visual_bert) # Uses ## Direct Use This model can be used for the task of question answering. ## Downstream Use [Optional] More information needed. ## Out-of-Scope Use The model should not be used to intentionally create hostile or alienating environments for people. # Bias, Risks, and Limitations Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. ## Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. # Training Details ## Training Data The model creators note in the [associated paper](https://arxiv.org/pdf/1908.03557.pdf): > We evaluate VisualBERT on four different types of vision-and-language applications: (1) Vi- sual Question Answering (VQA 2.0) (Goyal et al., 2017), Given an image and a question, the task is to correctly answer the question. We use the VQA 2.0 (Goyal et al., 2017), consisting of over 1 million questions about images from COCO. We train the model to predict the 3,129 most frequent answers and use image features from a ResNeXt-based (2) Visual Commonsense Reasoning (VCR) (Zellers et al., 2019), VCR consists of 290k questions derived from 110k movie scenes, where the questions focus on visual commonsense. (3) Natural Language for Visual Reasoning (NLVR2) (Suhr et al., 2019) NLVR2 is a dataset for joint reasoning about natural language and images, with a focus on semantic diversity, compositionality, and visual reasoning challenges. The task is to determine whether a natural language caption is true about a pair of images. The dataset consists of over 100k examples of English sentences paired with web images. We modify the segment embedding mechanism in VisualBERT and assign features from different images with different segment embeddings. (4) Region-to-Phrase Grounding (Flickr30K) (Plummer et al., 2015) >Flickr30K Entities dataset tests the ability of systems to ground phrases in captions to bounding regions in the image. The task is, given spans from a sentence, selecting the bounding regions they correspond to. The dataset consists of 30k images and nearly 250k annotations. ## Training Procedure ### Preprocessing The model creators note in the [associated paper](https://arxiv.org/pdf/1908.03557.pdf): > The parameters are initializedfromthepre-trainedBERTBASE parameters ### Speeds, Sizes, Times The model creators note in the [associated paper](https://arxiv.org/pdf/1908.03557.pdf): > The Transformer encoder in all models has the same configuration as BERTBASE: 12 layers, a hidden size of 768, and 12 self-attention heads. The parameters are initializedfromthepre-trainedBERTBASE parameters > Batch sizes are chosen to meet hardware constraints and text sequences whose lengths are longer than 128 are capped. # Evaluation ## Testing Data, Factors & Metrics ### Testing Data More information needed ### Factors More information needed ### Metrics More information needed ## Results More information needed # Model Examination More information needed # Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** Tesla V100s and GTX 1080Tis - **Hours used:** The model creators note in the [associated paper](https://arxiv.org/pdf/1908.03557.pdf) > Pre-training on COCO generally takes less than a day on 4 cards while task-specific pre-training and fine-tuning usually takes less - **Cloud Provider:** More information needed - **Compute Region:** More information needed - **Carbon Emitted:** More information needed # Technical Specifications [optional] ## Model Architecture and Objective More information needed ## Compute Infrastructure More information needed ### Hardware More information needed ### Software More information needed. # Citation **BibTeX:** ```bibtex @inproceedings{li2019visualbert, author = {Li, Liunian Harold and Yatskar, Mark and Yin, Da and Hsieh, Cho-Jui and Chang, Kai-Wei}, title = {VisualBERT: A Simple and Performant Baseline for Vision and Language}, booktitle = {Arxiv}, year = {2019} } ``` **APA:** More information needed # Glossary [optional] More information needed # More Information [optional] More information needed # Model Card Authors [optional] UCLA NLP in collaboration with Ezi Ozoani and the Hugging Face team # Model Card Contact More information needed # How to Get Started with the Model Use the code below to get started with the model.
Click to expand ```python from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("uclanlp/visualbert-vqa") model = AutoModelForQuestionAnswering.from_pretrained("uclanlp/visualbert-vqa") ```