Antonio Torralba

is this you? claim profile

∙ 1 follower
MIT ∙ Facebook

Assistant Professor of Electrical Engineering and Computer Science at Massachusetts Institute of Technology

Learning to See by Looking at Noise

Current vision systems are trained on huge datasets, and these datasets ...
06/10/2021 ∙ by Manel Baradad, et al. ∙ 0 ∙ share

read it
Measuring Generalization with Optimal Transport

Understanding the generalization of deep neural networks is one of the m...
06/07/2021 ∙ by Ching-Yao Chuang, et al. ∙ 0 ∙ share

read it
DriveGAN: Towards a Controllable High-Quality Neural Simulation

Realistic simulators are critical for training and verifying robotics sy...
04/30/2021 ∙ by Seung Wook Kim, et al. ∙ 56 ∙ share

read it
Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales

The past decade has witnessed a groundbreaking rise of machine learning ...
04/17/2021 ∙ by Jacob Andreas, et al. ∙ 21 ∙ share

read it
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort

We introduce DatasetGAN: an automatic procedure to generate massive data...
04/13/2021 ∙ by Yuxuan Zhang, et al. ∙ 40 ∙ share

read it
BARF: Bundle-Adjusting Neural Radiance Fields

Neural Radiance Fields (NeRF) have recently gained a surge of interest w...
04/13/2021 ∙ by Chen-Hsuan Lin, et al. ∙ 0 ∙ share

read it
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization

Training deep networks with limited labeled data while achieving a stron...
04/12/2021 ∙ by Daiqing Li, et al. ∙ 28 ∙ share

read it
The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI

We introduce a visually-guided and physics-driven task-and-motion planni...
03/25/2021 ∙ by Chuang Gan, et al. ∙ 16 ∙ share

read it
Paint by Word

We investigate the problem of zero-shot semantic image painting. Instead...
03/19/2021 ∙ by David Bau, et al. ∙ 6 ∙ share

read it
Deep Feedback Inverse Problem Solver

We present an efficient, effective, and generic approach towards solving...
01/19/2021 ∙ by Wei-Chiu Ma, et al. ∙ 0 ∙ share

read it
Energy-Based Models for Continual Learning

We motivate Energy-Based Models (EBMs) as a promising model class for co...
11/24/2020 ∙ by Shuang Li, et al. ∙ 1 ∙ share

read it
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration

In this paper, we introduce Watch-And-Help (WAH), a challenge for testin...
10/19/2020 ∙ by Xavier Puig, et al. ∙ 15 ∙ share

read it
Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

Differentiable rendering has paved the way to training neural networks t...
10/18/2020 ∙ by Yuxuan Zhang, et al. ∙ 10 ∙ share

read it
LID 2020: The Learning from Imperfect Data Challenge Results

Learning from imperfect data becomes an issue in many industrial applica...
10/17/2020 ∙ by Yunchao Wei, et al. ∙ 4 ∙ share

read it
Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space

Modern Generative Adversarial Networks are capable of creating artificia...
09/14/2020 ∙ by Jonas Wulff, et al. ∙ 0 ∙ share

read it
Understanding the Role of Individual Units in a Deep Neural Network

Deep neural networks excel at finding hierarchical representations that ...
09/10/2020 ∙ by David Bau, et al. ∙ 11 ∙ share

read it
The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement

Existing disentanglement methods for deep generative models rely on hand...
08/24/2020 ∙ by William Peebles, et al. ∙ 9 ∙ share

read it
Detecting natural disasters, damage, and incidents in the wild

Responding to natural disasters, such as earthquakes, floods, and wildfi...
08/20/2020 ∙ by Ethan Weber, et al. ∙ 4 ∙ share

read it
Rewriting a Deep Generative Model

A deep generative model such as a GAN learns to model a rich set of sema...
07/30/2020 ∙ by David Bau, et al. ∙ 12 ∙ share

read it
Noisy Agents: Self-supervised Exploration by Predicting Auditory Events

Humans integrate multiple sensory modalities (e.g. visual and audio) to ...
07/27/2020 ∙ by Chuang Gan, et al. ∙ 1 ∙ share

read it
Foley Music: Learning to Generate Music from Videos

In this paper, we introduce Foley Music, a system that can synthesize pl...
07/21/2020 ∙ by Chuang Gan, et al. ∙ 0 ∙ share

read it
Estimating Generalization under Distribution Shifts via Domain-Invariant Representations

When machine learning models are deployed on a test distribution differe...
07/06/2020 ∙ by Ching-Yao Chuang, et al. ∙ 0 ∙ share

read it
Causal Discovery in Physical Systems from Videos

Causal discovery is at the core of human cognition. It enables us to rea...
07/01/2020 ∙ by Yunzhu Li, et al. ∙ 0 ∙ share

read it
Debiased Contrastive Learning

A prominent technique for self-supervised representation learning has be...
07/01/2020 ∙ by Ching-Yao Chuang, et al. ∙ 0 ∙ share

read it
Diverse Image Generation via Self-Conditioned GANs

We introduce a simple but effective unsupervised method for generating r...
06/18/2020 ∙ by Steven Liu, et al. ∙ 12 ∙ share

read it
AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

Current methods for learning visually grounded language from videos ofte...
06/16/2020 ∙ by Andrew Rouditchenko, et al. ∙ 14 ∙ share

read it
Learning to Simulate Dynamic Environments with GameGAN

Simulation is a crucial component of any robotic system. In order to sim...
05/25/2020 ∙ by Seung Wook Kim, et al. ∙ 19 ∙ share

read it
Semantic Photo Manipulation with a Generative Image Prior

Despite the recent success of GANs in synthesizing images conditioned on...
05/15/2020 ∙ by David Bau, et al. ∙ 21 ∙ share

read it
Visual Grounding of Learned Physical Models

Humans intuitively recognize objects' physical properties and predict th...
04/28/2020 ∙ by Yunzhu Li, et al. ∙ 2 ∙ share

read it
Music Gesture for Visual Sound Separation

Recent deep learning approaches have achieved impressive performance on ...
04/20/2020 ∙ by Chuang Gan, et al. ∙ 2 ∙ share

read it
Self-supervised Moving Vehicle Tracking with Stereo Sound

Humans are able to localize objects in the environment using both visual...
10/25/2019 ∙ by Chuang Gan, et al. ∙ 10 ∙ share

read it
Seeing What a GAN Cannot Generate

Despite the success of Generative Adversarial Networks (GANs), mode coll...
10/24/2019 ∙ by David Bau, et al. ∙ 53 ∙ share

read it
Gaze360: Physically Unconstrained Gaze Estimation in the Wild

Understanding where people are looking is an informative social cue. In ...
10/22/2019 ∙ by Petr Kellnhofer, et al. ∙ 18 ∙ share

read it
Learning Compositional Koopman Operators for Model-Based Control

Finding an embedding space for a linear approximation of a nonlinear dyn...
10/18/2019 ∙ by Yunzhu Li, et al. ∙ 0 ∙ share

read it
The Role of Embedding Complexity in Domain-invariant Representations

Unsupervised domain adaptation aims to generalize the hypothesis trained...
10/13/2019 ∙ by Ching-Yao Chuang, et al. ∙ 0 ∙ share

read it
CLEVRER: CoLlision Events for Video REpresentation and Reasoning

The ability to reason about temporal and causal events from videos lies ...
10/03/2019 ∙ by Kexin Yi, et al. ∙ 12 ∙ share

read it
Connecting Touch and Vision via Cross-Modal Prediction

Humans perceive the world using multi-modal sensory inputs such as visio...
06/14/2019 ∙ by Yunzhu Li, et al. ∙ 4 ∙ share

read it
How to make a pizza: Learning a compositional layer-based GAN model

A food recipe is an ordered set of instructions for preparing a particul...
06/06/2019 ∙ by Dim P. Papadopoulos, et al. ∙ 0 ∙ share

read it
Meta-Sim: Learning to Generate Synthetic Datasets

Training models to high-end performance requires availability of large l...
04/25/2019 ∙ by Amlan Kar, et al. ∙ 12 ∙ share

read it
Self-Supervised Audio-Visual Co-Segmentation

Segmenting objects in images and separating sound sources in audio are c...
04/18/2019 ∙ by Andrew Rouditchenko, et al. ∙ 0 ∙ share

read it
The Sound of Motions

Sounds originate from object motions and vibrations of surrounding air. ...
04/11/2019 ∙ by Hang Zhao, et al. ∙ 0 ∙ share

read it
Visualizing and Understanding Generative Adversarial Networks (Extended Abstract)

Generative Adversarial Networks (GANs) have achieved impressive results ...
01/29/2019 ∙ by David Bau, et al. ∙ 22 ∙ share

read it
Visual Object Networks: Image Generation with Disentangled 3D Representation

Recent progress in deep generative models has led to tremendous breakthr...
12/06/2018 ∙ by Jun-Yan Zhu, et al. ∙ 8 ∙ share

read it
Dataset Distillation

Model distillation aims to distill the knowledge of a complex model into...
11/27/2018 ∙ by Tongzhou Wang, et al. ∙ 3 ∙ share

read it
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Generative Adversarial Networks (GANs) have recently achieved impressive...
11/26/2018 ∙ by David Bau, et al. ∙ 10 ∙ share

read it
Recipe1M: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images

In this paper, we introduce Recipe1M, a new large-scale, structured corp...
10/14/2018 ∙ by Javier Marin, et al. ∙ 0 ∙ share

read it
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

We marry two powerful ideas: deep representation learning for visual rec...
10/04/2018 ∙ by Kexin Yi, et al. ∙ 0 ∙ share

read it
Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids

Real-life control tasks involve matter of various substances---rigid or ...
10/03/2018 ∙ by Yunzhu Li, et al. ∙ 2 ∙ share

read it
Propagation Networks for Model-Based Control Under Partial Observation

There has been an increasing interest in learning dynamics simulators fo...
09/28/2018 ∙ by Yunzhu Li, et al. ∙ 4 ∙ share

read it
Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks

We introduce a saliency-based distortion layer for convolutional neural ...
09/10/2018 ∙ by Adria Recasens, et al. ∙ 8 ∙ share

read it

Antonio Torralba

Featured Co-authors