Samarth Mishra

Samarth Mishra, PhD Student in Computer Science, Advisors : Prof. Venkatesh Saligrama & Prof. Kate Saenko Boston University

Education

Interests

Computer Vision, Machine Learning

Publications

Conferences

• Y. Kim, Samarth Mishra, S. Jin, R. Panda, H. Kuehne, L. Karlinsky, V. Saligrama, K.Saenko, A. Oliva, R.S. Feris.
  How Transferable are Video Representations Based on Synthetic Data?
  NeurIPS 2022 D&B [openreview] [github]

• Samarth Mishra, R. Panda, C.P. Phoo, C.F. Chen, L. Karlinsky, K. Saenko, V. Saligrama, and R.S. Feris.
  Task2Sim: Towards effective pre-training and transfer from synthetic data.
  CVPR 2022 [arxiv] [project page]

• D. Bashkirova, D. Hendrycks, D. Kim, Samarth Mishra, K. Saenko, K. Saito, P. Teterwak, and B. Usman.
  Visda-2021 competition : Universal domain adaptation to improve performance on out-of-distribution data.
  NeurIPS 2021 Competitions Track. [arxiv] [competition page]

• Samarth Mishra, K. Saenko, and V. Saligrama.
  Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency.
  BMVC 2021 [arxiv] [github]

• Samarth Mishra, Z. Zhang, Y. Shen, R. Kumar, V. Saligrama, and B. Plummer.
  Effectively leveraging attributes for visual similarity.
  ICCV 2021 [arxiv] [github]

• S. Stojanov, Samarth Mishra, N.A. Thai, N. Dhanda,
  A. Humayun, L.B. Smith, C. Yu, and J. M. Rehg.
  Incremental Object Learning from Contiguous Views.
  Oral, Best paper finalist CVPR 2019 [cvf] [project page]

• K. Chatterjee, B. Kragl, Samarth Mishra, A. Pavlogiannis.
  Faster Algorithms for Weighted Recursive State Machines.
  ESOP 2017 [arxiv]

Workshops

• D. Kim, K. Saito, Samarth Mishra, S. Sclaroff, K. Saenko, and B.Plummer.
  Self-supervised visual attribute learning for fashion compatibility.
  ICCV 2021 VIPriors Workshop [arxiv]

• P. Zhu, R. Zhu, Samarth Mishra, and V. Saligrama.
  Low dimensional visual attributes: An interpretable image encoding.
  ICPR 2020 EDL/AI Workshop [springer]

Preprints

• Samarth Mishra, P. Zhu, V. Saligrama.
  Learning Compositional Representations for Effective Low-Shot Generalization. [arxiv]

Relevant Coursework

Boston University

• Towards Universal Natural Language Understanding

• Reinforcement Learning

• Statistical Learning Theory

Georgia Tech

• Machine Learning

• Numerical Linear Algebra

• Machine Learning Theory

IIT Bombay

• Advanced Machine Learning (Probabilistic Graphical Models and Deep Learning)

• Foundations of Intelligent and Learning Agents

• Algorithms in Medical Image Processing

• Digital Image Processing

Udacity

• Computer Vision

• Deep Learning

Find me on

Google Scholar
Twitter
Github
LinkedIn
Email: samarthm@bu.edu