Comments (2)
Thank you for your interest in our work!
1- In equations 11, 12, and 13 you are replacing the learned embeddings by a learnable constant, how this constant may be interpreted? what does it imply?
2- Why fixing this constant across the whole dimension, by multiplying it to ones?
The behind assumption is that if the image and question are blocked, the model would do a wild guess, i.e., each answer has the same probability to be selected. Therefore, we use the same constant to denote the same probability for all the candidate answers.
3- Following this,
z_qkv = self.fusion(logits, q_pred, v_pred, q_fact=True, k_fact=True, v_fact=True) # te z_q = self.fusion(logits, q_pred, v_pred, q_fact=True, k_fact=False, v_fact=False) # nie logits_cfvqa = z_qkv - z_q
if we neglect the non-linearity (z = torch.log(torch.sigmoid(z) + eps)), (z_qkv - z_q) will be interpreted as (z_k + z_q + z_v) - (2C + z_q) which means we can just rely from the beginning on z_k + z_v and remove the QA branch?! I think I misunderstand something here :D
That's why we use the non-linearity to fuse the three outputs. Such non-linear design is important to avoid the trial solution.
4- Is it possible to replace the constant with other real example, such as augmented version of the input or something like that, what do u think?
We tried that in our implementation, e.g, using a mean feature as the input, but it does not work well. This idea may work for other tasks.
from cfvqa.
Thank you very much for your prompt response and for the clarifications!
from cfvqa.
Related Issues (19)
- when to update HOT 2
- Where is the "block" module? HOT 1
- Typo on Command Line HOT 1
- Maybe something wrong in cfvqasimple.py HOT 8
- No such file or directory: 'data/vqa/coco/extract_rcnn/2018-04-27_bottom-up-attention_fixed_36/COCO_val2014_000000144334.jpg.pth' HOT 2
- Questions about the core idea HOT 2
- ModuleNotFoundError: No module named 'block.external' HOT 2
- How to extract image features? HOT 2
- What's the difference between train_split and proc_split? HOT 4
- How to get the accuracy of the overall test set and the accuray in Y/N, other and number HOT 2
- Question about evaluation strategy HOT 2
- smrl_cfvqa_rubi is TOO slow to train HOT 4
- Enquiries on reproducing the results HOT 2
- How to implement only update c when minimizing KL divergence? HOT 3
- TypeError: Object of type Tensor is not JSON serializable HOT 1
- updn_baseline.yaml
- What do these parameters mean๏ผ
- The weight in the loss computing.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from cfvqa.