Search Results for author: Sai Rajeswar

Found 12 papers, 6 papers with code

Multi-label Iterated Learning for Image Classification with Label Ambiguity

1 code implementation23 Nov 2021 Sai Rajeswar, Pau Rodriguez, Soumye Singhal, David Vazquez, Aaron Courville

We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision.

Image Classification Multi-Label Learning +1

Touch-based Curiosity for Sparse-Reward Tasks

1 code implementation1 Apr 2021 Sai Rajeswar, Cyril Ibrahim, Nitin Surya, Florian Golemo, David Vazquez, Aaron Courville, Pedro O. Pinheiro

Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion.

Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation

1 code implementation23 Mar 2020 Sai Rajeswar, Fahim Mannan, Florian Golemo, Jérôme Parent-Lévesque, David Vazquez, Derek Nowrouzezahrai, Aaron Courville

We propose Pix2Shape, an approach to solve this problem with four components: (i) an encoder that infers the latent 3D representation from an image, (ii) a decoder that generates an explicit 2. 5D surfel-based reconstruction of a scene from the latent code (iii) a differentiable renderer that synthesizes a 2D image from the surfel representation, and (iv) a critic network trained to discriminate between images generated by the decoder-renderer and those from a training distribution.

Adversarial Computation of Optimal Transport Maps

1 code implementation24 Jun 2019 Jacob Leygonie, Jennifer She, Amjad Almahairi, Sai Rajeswar, Aaron Courville

We show that during training, our generator follows the $W_2$-geodesic between the initial and the target distributions.

Pix2Scene: Learning Implicit 3D Representations from Images

no code implementations ICLR 2019 Sai Rajeswar, Fahim Mannan, Florian Golemo, David Vazquez, Derek Nowrouzezahrai, Aaron Courville

Modelling 3D scenes from 2D images is a long-standing problem in computer vision with implications in, e. g., simulation and robotics.

W2GAN: RECOVERING AN OPTIMAL TRANSPORT MAP WITH A GAN

no code implementations27 Sep 2018 Leygonie Jacob*, Jennifer She*, Amjad Almahairi, Sai Rajeswar, Aaron Courville

In this work we address the converse question: is it possible to recover an optimal map in a GAN fashion?

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

3 code implementations ICML 2018 Amjad Almahairi, Sai Rajeswar, Alessandro Sordoni, Philip Bachman, Aaron Courville

Learning inter-domain mappings from unpaired data can improve performance in structured prediction tasks, such as image segmentation, by reducing the need for paired data.

Semantic Segmentation Structured Prediction

Hierarchical Adversarially Learned Inference

no code implementations ICLR 2018 Mohamed Ishmael Belghazi, Sai Rajeswar, Olivier Mastropietro, Negar Rostamzadeh, Jovana Mitrovic, Aaron Courville

We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model.

MINE: Mutual Information Neural Estimation

18 code implementations12 Jan 2018 Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, R. Devon Hjelm

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks.

General Classification

Adversarial Generation of Natural Language

no code implementations WS 2017 Sai Rajeswar, Sandeep Subramanian, Francis Dutil, Christopher Pal, Aaron Courville

Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation.

Image Generation Language Modelling

A hypothesize-and-verify framework for Text Recognition using Deep Recurrent Neural Networks

no code implementations26 Feb 2015 Anupama Ray, Sai Rajeswar, Santanu Chaudhury

This paper proposes a hybrid text recognizer using a deep recurrent neural network with multiple layers of abstraction and long range context along with a language model to verify the performance of the deep neural network.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.