AIConfPaper
← Search

Samarth Sinha

17 accepted papers

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 +1
CVPR 2023highlight

Obtaining photorealistic reconstructions of objects from sparse views is inherently ambiguous and can only be achieved by learning suitable reconstruction priors. Earlier works on sparse rigid object reconstruction successfully learned such priors from large datasets such as CO3D. In this paper, we…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2023

SparsePose: Sparse-View Camera Pose Regression and Refinement

Samarth Sinha, Jason Y. Zhang, Andrea Tagliasacchi, Igor Gilitschenski, David B. Lindell
CVPR 2023poster

Camera pose estimation is a key step in standard 3D reconstruction pipelines that operates on a dense set of images of a single object or scene. However, methods for pose estimation often fail when there are only a few images available because they rely on the ability to robustly identify and match…

Cited by 45Source ↗PDF ↗Scholar ↗
2022

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

David Novotny, Ignacio Rocco, Samarth Sinha, Alexandre Carlier, Gael Kerchenbaum, Roman Shapovalov +4
CVPR 2022oral

We consider the problem of reconstructing the depth of dynamic objects from videos. Recent progress in dynamic video depth prediction has focused on improving the output of monocular depth estimators by means of multi-view constraints while imposing little to no restrictions on the deformation of th…

Cited by 13PDF ↗Scholar ↗
2022

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

Matthias Weissenbacher, Samarth Sinha, Animesh Garg, Kawahara Yoshinobu
ICML 2022spotlight

Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world settings where interactions are costly or dangerous. Current algorithms over-fit to the training dataset and as a consequence p…

Cited by 36Source ↗PDF ↗Scholar ↗
2021

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

Timo Milbich, Karsten Roth, Samarth Sinha, Ludwig Schmidt, Marzyeh Ghassemi, Björn Ommer
NeurIPS 2021poster

Deep Metric Learning (DML) aims to find representations suitable for zero-shot transfer to a priori unknown test distributions. However, common evaluation protocols only test a single, fixed data split in which train and test classes are assigned randomly. More realistic evaluations should consider…

Cited by 27Source ↗PDF ↗Scholar ↗
2021

DIBS: Diversity Inducing Information Bottleneck in Model Ensembles

Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti
AAAI 2021technical

Although deep learning models have achieved state-of-the art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research. Bayesian approaches including Bayesian Neural Nets (BNNs) d…

Cited by 53Source ↗PDF ↗Scholar ↗
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
IROS 2021poster

Learning from visual data opens the potential to accrue a large range of manipulation behaviors by leveraging human demonstrations without specifying each of them mathe-matically, but rather through natural task specification. In this paper, we present Learning by Watching (LbW), an algorithmic fram…

Cited by 91Source ↗Scholar ↗
2021

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

Samarth Sinha, Ajay Mandlekar, Animesh Garg
CoRL 2021poster

Offline reinforcement learning proposes to learn policies from large collected datasets without interacting with the physical environment. These algorithms have made it possible to learn useful skills from data that can then be deployed in the environment in real-world settings where interactions m…

Cited by 139Source ↗Scholar ↗
2020

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning

Timo Milbich, Karsten Roth, Homanga Bharadhwaj, Samarth Sinha, Yoshua Bengio, Björn Ommer +1
ECCV 2020poster

Visual Similarity plays an important role in many computer vision applications. Deep metric learning (DML) is a powerful framework for learning such similarities which not only generalize from training data to identically distributed test distributions, but in particular also translate to unknown te…

Cited by 79Source ↗PDF ↗code ↗Scholar ↗
2020

Revisiting Training Strategies and Generalization Performance in Deep Metric Learning

Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Bjorn Ommer, Joseph Paul Cohen
ICML 2020poster

Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year. Although the field benefits from the rapid progress, the divergence in training protocols, architectures, and parameter choices make an unbi…

Cited by 220Source ↗PDF ↗code ↗Scholar ↗
2020

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

Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena
ICML 2020poster

Recent work suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes. This finding is interesting but also discouraging – large batch sizes are slow and expensive to emulate on conventional hardware. Thus, it would be nice if there were some trick b…

Cited by 100Source ↗PDF ↗Scholar ↗
2020

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

Samarth Sinha, Zhengli Zhao, Anirudh Goyal ALIAS PARTH GOYAL, Colin A Raffel, Augustus Odena
NeurIPS 2020poster

We introduce a simple (one line of code) modification to the Generative Adversarial Network (GAN) training algorithm that materially improves results with no increase in computational cost. When updating the generator parameters, we simply zero out the gradient contributions from the elements of the…

Cited by 65Source ↗PDF ↗Scholar ↗
2019

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

Edgar Schonfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata
CVPR 2019poster

Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either images or image features. However, the former misses fine-grained…

Cited by 834PDF ↗code ↗Scholar ↗