March 3rd 2021 • 1 minute read

How to Implement Comparators (Greater than, Less than, Equal to) for your Python Classes

You have written a custom python class. Here is how to implement logic to check if instances of the class are equal, less than etc.

As you build applications that get fairly large in python, you will typically have to write classes that encapsulate functions, data classes that specify data values for or interface for exchanging data etc. In many cases you will want to also check things like equality, and if how things compare. For example, consider I have a dataclass for representing docuemnts ...

Each data class is used in representing data which is also persisited to a database

But each time I createa new Document, I want to know if it already exists. Now the id is

The technique employed is based on background matting, where an additional frame of the background is captured and used in recovering the alpha matte and the foreground layer. Source: Lin et al 2020.

Review TLDR;

Pros

Proposed model handles hair and subject boundary details much better than current approaches (think how Zoom might crop out hair portions or fail when your hand is close to your face or some other occlusion etc)
They improve speed/latency the state of the art for processing large images. Previous approaches that attempt fine grained segmentation achieve 8 fps on 512*512 images (pretty much unsuable). Their approach achieves 60FPS on HD images (1920*1080) and 30FPS on 4K images (3840×2160
They achieve these speed gains by using a two stage network. First network downsamples the image and outputs matte predictions + error prediction map at a low resolution. The second network (a refinement network) uses the low resolution result and original image to generate high-resolution output (fine grained detail) for only select regions of the image.
They compare their approach with several existing approaches and create a zoom plugin that pipes model output to zoom.
They provide sample code to reproduce their results and allow experimentation via notebooks.

Cons

- System requires specifying background image to work well. This is not a huge issue but introduces a new step (selecting background image) that might interfere with usability.
- The results (30FPS on HD images and 60FPS on HD images) are run on a GPU - Nvidia RTX 2080 TI GPU. This suggests it might still be unusable on CPUs (the majority of user environments)

Download the paper

Its pretty remarkable what has been accomplished here. Future work might benefit from:

Efforts to definitely would benefit from further optimizing for latency while maintaining fine grained segmentation (e.g. using residual U-blocks as proposed in the U2Net Paper. This might lead to usable FPS values on commodity CPU machines.
Efforts to optimize for usability by elmininating the background image requirement. E.g. by reframing the ML problem, we can train the network to jointly predict the background (image completion) in addition to the alpha matte values, and leverage this knowledge in predicting better matte values. Ideally, this formulation will utilize background images (as labels) during training but not require them during inference.

Overall, well written paper and well produced video explaining their work.

I will be updating this post as I experiment with the model itself.

References

Interested in more articles like this? Subscribe to get a monthly roundup of new posts and other interesting ideas at the intersection of Applied AI and HCI.

Read and Subscribe

← Previous

How to Implement Comparators (Greater than, Less than, Equal to) for your Python Classes

References

RELATED POSTS | howto, software engineering

Read the Newsletter.