Anurag Singh

I am a PhD student broadly interested in Trustworthy ML at Muandet Group @ Cispa Saarbr├╝cken. Previously, I obtained my Masters in Computer Science at the Technical University of Munich. I was also a Research Fellow with Prof. Soma Biswas in IACV LAB at Indian Institute of Science. I also worked as a Software Engineer in industry learning about how to write production ready computer vision software. I completed my BEng. from Netaji Subhas Institute of Technology, University of Delhi were I closely worked with Prof. A.V. Subramanyam .

CV  /  Projects  /  Blog  /  LinkedIn


I'm interested in computer vision and machine learning theory. My current research in computer vision is around perception where I work on tasks like classification, domain adaptation and retrieval under different constraints.

Improving Semi-Supervised Domain Adaptation Using Effective Target Selection and Semantics
Anurag Singh*, Naren Doraiswamy*, Sawa Takamuku, Megh Bhalerao, Titir Dutta
Soma Biswas, Aditya Chepuri
CVPR Workshop Learning with Limited and Imperfect Data, 2021
Adaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR
Titir Dutta, Anurag Singh, Soma Biswas
ECCV, 2020 (Spotlight Presentation ~5% acceptance rate)

We analyze the effect of class-imbalance on generalization to unseen classes for the ZS-SBIR. The work then proposes a novel regularizer termed AMDReg, which can seamlessly be used with several ZS-SBIR methods to improve their performance.

StyleGuide: Zero-Shot Sketch-based Image Retrieval Using Style-Guided Image Generation
Titir Dutta, Anurag Singh, Soma Biswas
IEEE Transactions on Multimedia, 2020

A style-guided image generation during retrieval to eliminate the effect of domain difference and intra-class variations.

Image Corpus Representative Summarization
Anurag Singh, Lakshay Virmani, AV Subramanyam
IEEE International Conference on Multimedia Big Data, 2019
(Honourable Mention Award, Best Paper Nomination)

This work is part of my undergraduate thesis which focused on developing end to end deep learning architecture for problem of Image Collection Summarization. We introduced a task-specific loss to generate the summary related to a given task. We also proposed analysis of goodness of summary by training a classifier on it and comparing its performance with entire dataset.

Technical Reports (Click to expand!)
Recent News (click to expand!)