Useful Information:

This page will contain details regarding the Course Projects.

Students are encouraged to select a topic and work on their own projects. However, it is highly recommended that students talk to members of various labs at IISc who are experienced in the topic they have selected.

Projects can be broadly classified of two kinds:

  1. Application
    : when Deep learning is used for image processing in other research fields. For example, medical tool segmentation in operation videos.
  2. Improving Deep learning architectures
    : when interesting new ideas are introduced to pre-existing models for improving their performance. For example, exploring benefits of higher dimensional convolution in a traditional classification setup.

As the course is on using Deep Learning for Computer Vision, the project must visual data in form of pixels etc.


Some resources for selecting projects:

For models, ConvNets have been successfully used in a variety of computer vision tasks. This type of projects would involve understanding the state-of-the-art vision models, and building new models or improving existing models for a vision task. The list below presents some papers on recent advances of ConvNets in the computer vision community.


We also provide a list of popular computer vision datasets:

Grading Policy

This information will be added soon.

Some Example Projects

Projects at VAL, by the present PhD. students will be added to this google doc. Link to Google Doc

Projects in a similar course at Stanford has been listed here. These can help guide you.


Material from CS231n has been used for preparing this page, as well as the basic course material.