[docs] Add UNITER model to website

Add citation and training instructions under projects/uniter.

ghstack-source-id: 72443b8
Pull Request resolved: #1144

Author: Ryan-Qiyu-Jiang

website/docs/notes/model_zoo.md

@@ -23,6 +23,8 @@ Here is the list of models currently implemented in MMF:
 | Unimodal        | unimodal                             | hateful_memes                            |                                                             |
 | VilBERT         | vilbert                              | hateful_memes, coco, conceptual_captions, mmimdb, nlvr2, visual_entailment, vizwiz, vqa2 |[paper](https://arxiv.org/abs/1908.02265)|
 | ViLT            | vilt                                 | coco, vqa2                               |[paper](https://arxiv.org/pdf/2102.03334)                    |
+| UNITER          | uniter                               | vqa2, masked_coco                        | [paper](https://arxiv.org/abs/1909.11740)                   |
+| VilBERT         | vilbert                              | hateful_memes, coco, conceptual_captions, vqa2, mmimdb, nlvr2, visual_entailment, vizwiz, vqa2 |[paper](https://arxiv.org/abs/1908.02265)|
 | Visual BERT     | visual_bert                          | gqa, hateful_memes, localized_narratives, coco, conceptual_captions, sbu, vqa2, mmimdb, nlvr2, visual_entailment, vizwiz|[paper](https://arxiv.org/abs/1908.03557)|
 
 We are adding many more new models which will be available soon.

website/docs/projects/uniter.md

@@ -0,0 +1,48 @@
+---
+id: uniter
+sidebar_label: UNITER
+title: "UNITER: UNiversal Image-TExt Representation Learning"
+---
+
+This repository contains the code for pytorch implementation of UNITER model, released originally under this ([repo](https://github.com/ChenRocks/UNITER)). Please cite the following papers if you are using UNITER model from mmf:
+
+* Chen, Y.-C., Li, L., Yu, L., Kholy, A. E., Ahmed, F., Gan,
+Z., Cheng, Y., and jing Liu, J. *Uniter: Universal imagetext representation learning.* In European Conference on
+Computer Vision, 2020b. ([arXiV](https://arxiv.org/pdf/1909.11740))
+```
+@inproceedings{chen2020uniter,
+  title={Uniter: Universal image-text representation learning},
+  author={Chen, Yen-Chun and Li, Linjie and Yu, Licheng and Kholy, Ahmed El and Ahmed, Faisal and Gan, Zhe and Cheng, Yu and Liu, Jingjing},
+  booktitle={ECCV},
+  year={2020}
+}
+```
+
+## Installation
+
+Follow installation instructions in the [documentation](https://mmf.readthedocs.io/en/latest/notes/installation.html).
+
+## Training
+
+To train a fresh UNITER model on the VQA2.0 dataset, run the following command
+```
+mmf_run config=projects/uniter/configs/vqa2/defaults.yaml run_type=train_val dataset=vqa2 model=uniter
+```
+
+To finetune a pretrained UNITER model on the VQA2.0 dataset,
+```
+mmf_run config=projects/uniter/configs/vqa2/defaults.yaml run_type=train_val dataset=vqa2 model=uniter checkpoint.resume_zoo=uniter.pretrained
+```
+
+To finetune a pretrained [VILLA](https://arxiv.org/pdf/2006.06195.pdf) model on the VQA2.0 dataset,
+```
+mmf_run config=projects/uniter/configs/vqa2/defaults.yaml run_type=train_val dataset=vqa2 model=uniter checkpoint.resume_zoo=villa.pretrained
+```
+
+To pretrain UNITER on the masked COCO dataset, run the following command
+```
+mmf_run config=projects/uniter/configs/masked_coco/defaults.yaml run_type=train_val dataset=masked_coco model=uniter
+```
+
+
+Based on the config used and `do_pretraining` defined in the config, the model can use the pretraining recipe described in the UNITER paper, or be finetuned on downstream tasks.

website/sidebars.js

@@ -45,6 +45,6 @@ module.exports = {
       'challenges/textvqa_challenge',
       'challenges/vqa_challenge',
     ],
-    Projects: ['projects/butd', 'projects/m4c', 'projects/m4c_captioner', 'projects/movie_mcan', 'projects/unit', 'projects/vilt'],
+    Projects: ['projects/butd', 'projects/m4c', 'projects/m4c_captioner', 'projects/movie_mcan', 'projects/unit', 'projects/vilt', 'projects/uniter'],
   },
 };