Put FasterRCNN steps in Beta Expander

apps/article.py

@@ -303,7 +303,10 @@ def app(state=None):
     toc.placeholder()
     
     toc.header("Introduction and Motivation")
-    st.write(read_markdown("intro/intro.md"))
+    st.write(read_markdown("intro/intro_part_1.md"))
+    with st.beta_expander("FasterRCNN Approach"):
+        st.write(read_markdown("intro/faster_rcnn_approach.md"))
+    st.write(read_markdown("intro/intro_part_2.md"))
     toc.subheader("Novel Contributions")
     st.write(read_markdown("intro/contributions.md"))
     

sections/intro/faster_rcnn_approach.md

@@ -0,0 +1,6 @@
+For example, a FasterRCNN approach uses the following steps:
+- the image features are given out by a FPN (Feature Pyramid Net) over a ResNet backbone, and
+- then a RPN (Regision Proposal Network) layer detects proposals in those features, and
+- then the ROI (Region of Interest) heads get the box proposals in the original image, and
+- the the boxes are selected using a NMS (Non-max suppression),
+- and then the features for selected boxes are used as visual features.

sections/intro/intro_part_1.md

@@ -0,0 +1,3 @@
+Visual Question Answering (VQA) is a task where we expect the AI to answer a question about a given image. VQA has been an active area of research for the past 4-5 years, with most datasets using natural images found online. Two examples of such datasets are: [VQAv2](https://visualqa.org/challenge.html), [GQA](https://cs.stanford.edu/people/dorarad/gqa/about.html). VQA is a particularly interesting multi-modal machine learning challenge because it has several interesting applications across several domains including healthcare chatbots, interactive-agents, etc. **However, most VQA challenges or datasets deal with English-only captions and questions.** 
+
+In addition, even recent **approaches that have been proposed for VQA generally are obscure** due to the fact that CNN-based object detectors are relatively difficult to use and more complex for feature extraction. Click on the expandable region below to see steps for FasterRCNN-based approach.

sections/intro/{intro.md → intro_part_2.md}

@@ -1,12 +1,3 @@
-Visual Question Answering (VQA) is a task where we expect the AI to answer a question about a given image. VQA has been an active area of research for the past 4-5 years, with most datasets using natural images found online. Two examples of such datasets are: [VQAv2](https://visualqa.org/challenge.html), [GQA](https://cs.stanford.edu/people/dorarad/gqa/about.html). VQA is a particularly interesting multi-modal machine learning challenge because it has several interesting applications across several domains including healthcare chatbots, interactive-agents, etc. **However, most VQA challenges or datasets deal with English-only captions and questions.** 
-
-In addition, even recent **approaches that have been proposed for VQA generally are obscure** due to the fact that CNN-based object detectors are relatively difficult to use and more complex for feature extraction. For example, a FasterRCNN approach uses the following steps:
-- the image features are given out by a FPN (Feature Pyramid Net) over a ResNet backbone, and
-- then a RPN (Regision Proposal Network) layer detects proposals in those features, and
-- then the ROI (Region of Interest) heads get the box proposals in the original image, and
-- the the boxes are selected using a NMS (Non-max suppression),
-- and then the features for selected boxes are used as visual features.
-
 A major **advantage that comes from using transformers is their simplicity and their accessibility** - thanks to HuggingFace, ViT and Transformers. For ViT models, for example, all one needs to do is pass the normalized images to the transformer.
 
 While building a low-resource non-English VQA approach has several benefits of its own, a multilingual VQA task is interesting because it will help create a generic model that works well across several languages. And then, it can be fine-tuned in low-resource settings to leverage pre-training improvements. **With the aim of democratizing such a challenging yet interesting task, in this project, we focus on Mutilingual Visual Question Answering (MVQA)**. Our intention here is to provide a Proof-of-Concept with our simple CLIP-Vision-BERT baseline which leverages a multilingual checkpoint with pre-trained image encoders. Our model currently supports for four languages - **English, French, German and Spanish**.