Pramesh Gautam

I want to compute where the point (x,y) in the image is mapped to after applying the transformation. How can this be done in airlab?

I was going through the code of BSplineTransformation. I was trying to relate is to this [paper](https://ieeexplore.ieee.org/abstract/document/796284/) as stated in airlab's paper. However, I am not able to relate how...

Clarification on in-between class samples results

1

In the paper, Figure 5b (Analysis for in-between class samples) is explained as **the probability to predict neither two classes by varying the combination ratio lambda**. Does it mean that...

There are 75 images that have 5 lanes but the architecture is to detect 5 categories (background + 4 lanes). I have removed those images from training and used the...

Hi In standard resnet18 from [Pytorch](https://pytorch.org/vision/main/generated/torchvision.models.resnet18.html), when `3,224,224` input is fed, `layer4` should output feature map of size `512x7x7`. However, in your repo, the final layer feature size is `512x28x28`....

I'm not able to understand how the masked classification score is computed. In the paper it says **input images are masked by the corresponding segmentations**. How can the images be...

I tried passing a 2D image of the plane from PASCAL VOC dataset to replicate the results shown in Fig. 4a. The image attached below was passed. However, while running...

Q: Why rotary embedding applied only to queries and keys?

1

In the codebase, rotary embeddings are applied only to queries and keys but not to values. Can someone point out to reasons/papers behind this design? Thank you in advance!!!