Update README.md

README.md

@@ -22,6 +22,8 @@ The model was pretrained model on English language using masked language modelin
 The abstract from the paper is the following:
 Vision-Language (VL) models with the Two-Tower architecture have dominated visual-language representation learning in recent years. Current VL models either use lightweight uni-modal encoders and learn to extract, align and fuse both modalities simultaneously in a deep cross-modal encoder, or feed the last-layer uni-modal representations from the deep pre-trained uni-modal encoders into the top cross-modal encoder. Both approaches potentially restrict vision-language representation learning and limit model performance. In this paper, we propose BridgeTower, which introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. This enables effective bottom-up cross-modal alignment and fusion between visual and textual representations of different semantic levels of pre-trained uni-modal encoders in the cross-modal encoder. Pre-trained with only 4M images, BridgeTower achieves state-of-the-art performance on various downstream vision-language tasks. In particular, on the VQAv2 test-std set, BridgeTower achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data and almost negligible additional parameters and computational costs. Notably, when further scaling the model, BridgeTower achieves an accuracy of 81.15%, surpassing models that are pre-trained on orders-of-magnitude larger datasets.
 
+BridgeTower got accepted to [AAAI'23](https://aaai.org/Conferences/AAAI-23/).
+
 ## Intended uses & limitations(TODO)
 
 You can use the raw model for masked language modeling, but it's mostly intended to be fine-tuned on a downstream task.
@@ -38,18 +40,16 @@ from PIL import Image
 
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
-text = "a bunch of [MASK] laying on a [MASK]."
-# Masked Language Modeling
+text = "hello world"
+
 processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-base")
-model = BridgeTowerForMaskedLM.from_pretrained("BridgeTower/bridgetower-base")
+model = BridgeTowerForModel.from_pretrained("BridgeTower/bridgetower-base")
 # Prepare inputs
 encoding = processor(image, text, return_tensors="pt")
 # Forward pass
 outputs = model(**encoding)
-# Image and Text Retrieval
-model = BridgeTowerForImageAndTextRetrieval.from_pretrained("BridgeTower/bridgetower-base")
-# Image and Text Classification
-model = BridgeTowerForImageAndTextClassification.from_pretrained("BridgeTower/bridgetower-base")
+outputs.keys()
+odict_keys(['text_feats', 'image_feats', 'pooler_output'])
 ```
 ### Limitations and bias
 
@@ -77,11 +77,9 @@ The model was pre-trained for 100k steps on 8 NVIDIA A100 GPUs with a batch size
 The optimizer used was AdamW with a learning rate of 1e-5. No data augmentation was used except for center-crop. The image resolution in pre-training is set to 288 x 288. 
 
 ## Evaluation results
-When fine-tuned on downstream tasks, this model achieves the following results:
 
-| Task | | | | | | | | |
-|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|
-| | | | | | | | | |
+Please refer to [Table 5](https://arxiv.org/pdf/2206.08657.pdf) for BridgeTower's performance on Image Retrieval and other down stream tasks. 
+
 
 ### BibTeX entry and citation info
 ```bibtex