license: apache-2.0
tags:
- visual_bert
- transformers
- image-to-text
- image-captioning
Model Card for visualbert-vcr
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]: Gunjan Chhablani
Model type: Image to Text
Language(s) (NLP): More information needed
License: Apache 2.0
Parent Model: More information needed
Resources for more information:
Uses
Direct Use
This model can be used for vision-and-language (V&L) tasks on image-caption data.
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) and Bender et al. (2021)). 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:
We evaluate VisualBERT on four different types of vision-and-language applications: (1) Vi- sual Question Answering (VQA 2.0): 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): VCR consists of 290k questions derived from 110k movie scenes, where the questions focus on visual commonsense. (3) Natural Language for Visual Reasoning (NLVR2): 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) 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:
The parameters are initializedfromthepre-trainedBERTBASE parameters
Speeds, Sizes, Times
The model creators note in the associated paper:
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
See associated paper for more inforamtion.
Model Examination
More information needed
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: Tesla V100s and GTX 1080Tis
- Hours used:
The model creators note in the associated paper:
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
The model creators note in the associated paper:
Experiments are conducted on Tesla V100s and GTX 1080Tis, and all experiments can be replicated on at most 4 Tesla V100s each with 16GBs of GPU memory.
Software
More information needed.
Citation
BibTeX:
@misc{https://doi.org/10.48550/arxiv.1908.03557,
doi = {10.48550/ARXIV.1908.03557},
url = {https://arxiv.org/abs/1908.03557},
author = {Li, Liunian Harold and Yatskar, Mark and Yin, Da and Hsieh, Cho-Jui and Chang, Kai-Wei},
keywords = {Computer Vision and Pattern Recognition (cs.CV), Computation and Language (cs.CL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {VisualBERT: A Simple and Performant Baseline for Vision and Language},
publisher = {arXiv},
year = {2019},
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
from transformers import AutoTokenizer, AutoModelForMultipleChoice
tokenizer = AutoTokenizer.from_pretrained("uclanlp/visualbert-vcr")
model = AutoModelForMultipleChoice.from_pretrained("uclanlp/visualbert-vcr")