Search Results for author:
Found 28 papers, 12 papers with code
Going Deeper with Convolutions
We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014).
Critic Regularized Regression
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction.
SSD: Single Shot MultiBox Detector
Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.
Ranked #3 on
Object Detection
on PASCAL VOC 2012
Scaling data-driven robotics with reward sketching and batch reinforcement learning
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
Generative Adversarial Text to Image Synthesis
Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal.
Learning Deep Representations of Fine-grained Visual Descriptions
State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information.
A Generalist Agent
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs.
Ranked #1 on
Skill Generalization
on RGB-Stacking
Learning Compositional Neural Programs with Recursive Tree Search and Planning
AlphaZero contributes powerful neural network guided search algorithms, which we augment with recursion.
Evaluation of Output Embeddings for Fine-Grained Image Classification
Image classification has advanced significantly in recent years with the availability of large-scale image sets.
Neural Programmer-Interpreters
We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs.
Training Deep Neural Networks on Noisy Labels with Bootstrapping
On MNIST handwritten digits, we show that our model is robust to label corruption.
Neural Arithmetic Logic Units
Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training.
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels.
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet.
Robust Imitation of Diverse Behaviors
Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train.
Parallel Multiscale Autoregressive Density Estimation
Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images.
Ranked #2 on
Image Compression
on ImageNet32
Learning What and Where to Draw
Generative Adversarial Networks (GANs) have recently demonstrated the capability to synthesize compelling real-world images, such as room interiors, album covers, manga, faces, birds, and flowers.
Ranked #13 on
Text-to-Image Generation
on CUB
(using extra training data)
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
An important problem for both graphics and vision is to synthesize novel views of a 3D object from a single image.
Scalable, High-Quality Object Detection
Using the multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with $0. 5$ mAP for a single model and $0. 52$ mAP for an ensemble of two models.
Sample Efficient Adaptive Text-to-Speech
Instead, the aim is to produce a network that requires few data at deployment time to rapidly adapt to new speakers.
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators.
Visual Imitation with a Minimal Adversary
The proposed agent can solve a challenging robot manipulation task of block stacking from only video demonstrations and sparse reward, in which the non-imitating agents fail to learn completely.
Task-Relevant Adversarial Imitation Learning
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels.
Offline Learning from Demonstrations and Unlabeled Experience
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
Semi-supervised reward learning for offline reinforcement learning
In offline reinforcement learning (RL) agents are trained using a logged dataset.
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains.
RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task.
Genie: Generative Interactive Environments
We introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos.
