Search Results for author:
Found 19 papers, 7 papers with code
Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation
Learning generalizeable policies from visual input in the presence of visual distractions is a challenging problem in reinforcement learning.
Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models
Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space.
A Dot Product Attention Free Transformer
We introduce Dot Product Attention Free Transformer (DAFT), an efficient variant of Transformers \citep{transformer} that eliminates the query-key dot product in self attention.
Ranked #620 on
Image Classification
on ImageNet
An Attention Free Transformer
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
Unconstrained Scene Generation with Locally Conditioned Radiance Fields
In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera.
Ranked #1 on
Scene Generation
on VizDoom
Uncertainty Weighted Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
On the generalization of learning-based 3D reconstruction
State-of-the-art learning-based monocular 3D reconstruction methods learn priors over object categories on the training set, and as a result struggle to achieve reasonable generalization to object categories unseen during training.
Capsules with Inverted Dot-Product Attention Routing
We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote.
Geometric Capsule Autoencoders for 3D Point Clouds
The pose encodes where the entity is, while the feature encodes what it is.
Initialization Strategies of Spatio-Temporal Convolutional Neural Networks
We propose a new way of incorporating temporal information present in videos into Spatial Convolutional Neural Networks (ConvNets) trained on images, that avoids training Spatio-Temporal ConvNets from scratch.
Exploiting Image-trained CNN Architectures for Unconstrained Video Classification
Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34. 95% to 38. 74%.
Unsupervised Learning of Video Representations using LSTMs
We further evaluate the representations by finetuning them for a supervised learning problem - human action recognition on the UCF-101 and HMDB-51 datasets.
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
The key idea is to randomly drop units (along with their connections) from the neural network during training.
Learning Generative Models with Visual Attention
Our model is a proper graphical model where the 2D Similarity transformation is a part of the top-down process.
Discriminative Transfer Learning with Tree-based Priors
The tree structure can be used to impose a generative prior over classification parameters.
Ranked #183 on
Image Classification
on CIFAR-100
Modeling Documents with Deep Boltzmann Machines
We introduce a Deep Boltzmann Machine model suitable for modeling and extracting latent semantic representations from a large unstructured collection of documents.
Multimodal Learning with Deep Boltzmann Machines
Our experimental results on bi-modal data consisting of images and text show that the Multimodal DBM can learn a good generative model of the joint space of image and text inputs that is useful for information retrieval from both unimodal and multimodal queries.
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data.
Ranked #205 on
Image Classification
on CIFAR-10
