Deepak Kumar Singh

I'm an MS by Research student at CVIT, IIIT Hyderabad. I'm advised by Prof. C.V. Jawahar. I was fortunate to be co-advised by Prof. Vineeth N Balasubramanian, Prof. Chetan Arora, Dr. Anbumani Subramanian. My general areas of interest are Computer Vision, Deep Learning and Machine Learning. I'm also interested in solving problems related to Semi-Supervised, Life-long Learning / Incremental Learning / Continual Learning.

I like photography, majorly urban photography and landscapes; check out my Flickr. I've recently started learning Bansuri(Indian Flute). To know what I'm currently reading, checkout my Goodreads.

Email: deepaksinghcv@gmail.com

|    CV  /  Twitter  /  Github     | 

profile photo

---- Looking for full-time research jobs/internships. ----

Research

I'm interested to work in Incremental/Continual/Life-long Learning. I have worked on road scene datasets and have addressed various issues present in them. My recent publications are based on autonomous driving scenarios. Authors marked with a * have an equal contribution in the research.

News
  • [Dec 2021] : Presented our work, "ORDER: Open World Object Detection on Road Scenes" at NeurIPS Workshop on Machine Learning for Autonomous Driving 2021.
  • [Dec 2021] : Presented our work, "Evaluation of Detection and Segmentation Tasks on Driving Datasets" at CVIP 2021.
  • [Oct 2021] : 🎉 One paper accepted in NeurIPS Workshop on Machine Learning for Autonomous Driving 2021.
  • [Oct 2021] : 🎉 One paper accepted in CVIP 2021 for Oral presentation.
  • [Aug 2021] : In the organizing team for IIIT-H's annual Summer School Program
  • [Aug 2020] : Joined Vision for Mobility and Safety Team in CVIT.
  • [Nov 2019] : Attended NCVPRIPG at Hubbali, Karnataka.
  • [Jan 2019] : Joined CVIT as a Research Fellow.
  • [Dec 2018] : Got the opportunity to attend ICVGIP 2018 and talk to various speakers and fellow researchers.
  • [Aug 2018] : Joined IIIT-H as an MS by Research student.
Publications
ORDER: Open World Object Detection on Road Scenes
Deepak Kumar Singh*, Shyam Nandan Rai*, K J Joseph, Rohit Saluja,
Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian, C.V. Jawahar
NeurIPS 2021 Workshop on Machine Learning for Autonomous Driving
Poster / Paper / Video(Soon) /

This work formulates Open-World Object Detection by addressing the inherent issues present in road scene datasets India Driving Dataset(IDD) and Berkeley Deep Drive(BDD).

Evaluation of Detection and Segmentation Tasks on Driving Datasets
Deepak Kumar Singh, Ameet Rahane, Ajoy Mondal, Anbumani Subramanian, C.V. Jawahar
CVIP, 2021 (Oral)
Paper / Project Page(Soon) / Slides(Soon) / Video(Soon) /

Benchmark latest models of object detection, semantic segmentation, and instance segmentation on road scene datasets. We perform a detailed study on their behaviour on both constrained and unconstrained datasets; Cityscapes, India Driving Dataset(IDD) and Berkeley Deep Drive(BDD).

Voluntary Services

I'm also a student system administrator for IIIT-Hyderabad's HPC cluster consisting of 252 GPUs. I help in creating, managing, and reserving slurm accounts for the CVIT Lab.

Template from here and here. Thank you :)

Last Updated: 17th January 2022