Samarth Sinha

According to our database, Samarth Sinha authored at least 29 papers between 2019 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Δ-Networks for Efficient Model Patching.

Chaitanya Devaguptapu, Samarth Sinha, K. J. Joseph, Vineeth N. Balasubramanian, Animesh Garg

CoRR, 2023

TeST: Test-time Self-Training under Distribution Shift.

Samarth Sinha, Peter V. Gehler, Francesco Locatello, Bernt Schiele

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categories.

Samarth Sinha, Roman Shapovalov, Jeremy Reizenstein, Ignacio Rocco, Natalia Neverova, Andrea Vedaldi, David Novotný

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

SparsePose: Sparse-View Camera Pose Regression and Refinement.

Samarth Sinha, Jason Y. Zhang, Andrea Tagliasacchi, Igor Gilitschenski, David B. Lindell

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Offline Policy Optimization in RL with Variance Regularizaton.

Riashat Islam, Samarth Sinha, Homanga Bharadhwaj, Samin Yeasar Arnob, Zhuoran Yang, Animesh Garg, Zhaoran Wang, Lihong Li, Doina Precup

CoRR, 2022

Stackmix: a complementary mix algorithm.

John Chen, Samarth Sinha, Anastasios Kyrillidis

Proceedings of the Uncertainty in Artificial Intelligence, 2022

Experience Replay with Likelihood-free Importance Weights.

Samarth Sinha, Jiaming Song, Animesh Garg, Stefano Ermon

Proceedings of the Learning for Dynamics and Control Conference, 2022

Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics.

Matthias Weissenbacher, Samarth Sinha, Animesh Garg, Yoshinobu Kawahara

Proceedings of the International Conference on Machine Learning, 2022

Uniform Priors for Data-Efficient Learning.

Samarth Sinha, Karsten Roth, Anirudh Goyal, Marzyeh Ghassemi, Zeynep Akata, Hugo Larochelle, Animesh Garg

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

KeyTr: Keypoint Transporter for 3D Reconstruction of Deformable Objects in Videos.

David Novotný, Ignacio Rocco, Samarth Sinha, Alexandre Carlier, Gael Kerchenbaum, Roman Shapovalov, Nikita Smetanin, Natalia Neverova, Benjamin Graham, Andrea Vedaldi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning.

Samarth Sinha, Animesh Garg

CoRR, 2021

Consistency Regularization for Variational Auto-Encoders.

Samarth Sinha, Adji Bousso Dieng

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning.

Timo Milbich, Karsten Roth, Samarth Sinha, Ludwig Schmidt, Marzyeh Ghassemi, Björn Ommer

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos.

Haoyu Xiong, Quanzhou Li, Yun-Chun Chen, Homanga Bharadhwaj, Samarth Sinha, Animesh Garg

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021

S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning in Robotics.

Samarth Sinha, Ajay Mandlekar, Animesh Garg

Proceedings of the Conference on Robot Learning, 8-11 November 2021, London, UK., 2021

DIBS: Diversity Inducing Information Bottleneck in Model Ensembles.

Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

ImCLR: Implicit Contrastive Learning for Image Classification.

John Chen, Samarth Sinha, Anastasios Kyrillidis

CoRR, 2020

D2RL: Deep Dense Architectures in Reinforcement Learning.

Samarth Sinha, Homanga Bharadhwaj, Aravind Srinivas, Animesh Garg

CoRR, 2020

Maximum Entropy Models for Fast Adaptation.

Samarth Sinha, Anirudh Goyal, Animesh Garg

CoRR, 2020

Curriculum By Texture.

Samarth Sinha, Animesh Garg, Hugo Larochelle

CoRR, 2020

Top-K Training of GANs: Improving Generators by Making Critics Less Critical.

Samarth Sinha, Anirudh Goyal, Colin Raffel, Augustus Odena

CoRR, 2020

Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples.

Samarth Sinha, Zhengli Zhao, Anirudh Goyal, Colin Raffel, Augustus Odena

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Curriculum By Smoothing.

Samarth Sinha, Animesh Garg, Hugo Larochelle

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Small-GAN: Speeding up GAN Training using Core-Sets.

Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena

Proceedings of the 37th International Conference on Machine Learning, 2020

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning.

Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Björn Ommer, Joseph Paul Cohen

Proceedings of the 37th International Conference on Machine Learning, 2020

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning.

Timo Milbich, Karsten Roth, Homanga Bharadhwaj, Samarth Sinha, Yoshua Bengio, Björn Ommer, Joseph Paul Cohen

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Variational Adversarial Active Learning.

Samarth Sinha, Sayna Ebrahimi, Trevor Darrell

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Generalized Zero-Shot Learning via Aligned Variational Autoencoders.

Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders.

Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019