Aadarsh Sahoo

I am a final year undergraduate student at the Department of Computer Science and Engineering at the Indian Institute of Technology (IIT) Kharagpur, India.

At IIT Kharagpur, apart from my academics, I work as an undergraduate researcher at the Computer Vision and Intelligence Research Lab under the supervision of Prof. Abir Das. I am also actively collaborating with Dr. Rameswar Panda and Dr. Rogerio Feris from the MIT-IBM Watson AI Lab.

In the summer of 2021, I was fortunate enough to get an opportunity to work under the guidance of Prof. Kate Saenko (Boston University) and Prof. Trevor Darrell (UC Berkeley), as a research intern for the DARPA LwLL Project.

Email  /  Google Scholar  /  Resume  /  LinkedIn  /  Github

profile photo

My research interests lie broadly in computer vision and artificial intelligence. My current focus majorly is to explore and conduct fundamental computer vision research with limited supervision, with a goal to conduct research and design products benefiting humanity. I am excited to be part of this fast-evolving and fascinating field, and I hope to contribute to its growth.

Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing
Aadarsh Sahoo, Rutav Shah, Rameswar Panda, Kate Saenko, Abir Das
35th Conference on Neural Information Processing Systems (NeurIPS), 2021.
project page / code

We introduce a novel temporal contrastive learning approach for unsupervised video domain adaptation, which is achieved by jointly leveraging video speed, background mixing, and target pseudo-labels.

Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
Aadarsh Sahoo, Rameswar Panda, Rogerio Feris, Kate Saenko, Abir Das
NeurIPS DistShift Workshop (NeurIPS-W), 2021 (Extended version under review).
project page / code

We develop a novel 'Select, Label, and Mix' (SLM) framework that aims to learn discriminative invariant feature representations for partial domain adaptation.

Mitigating Dataset Imbalance via Joint Generation and Classification
Aadarsh Sahoo, Ankit Singh, Rameswar Panda, Rogerio Feris, Abir Das
ECCV Workshop on Imbalance Problems in Computer Vision (ECCV-W), 2020 (Oral 10 min talk).
project page / code / live talk

We introduce a joint dataset repairment strategy by combining classifier with a GAN that makes up for the deficit of training examples from the minority class by producing additional examples.


Webpage template courtesy: Jon Barron