Search Results for author:
Found 28 papers, 14 papers with code
S3TA: A Soft, Spatial, Sequential, Top-Down Attention Model
We present a soft, spatial, sequential, top-down attention model (S3TA).
Learning from One Continuous Video Stream
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling.
SODA: Bottleneck Diffusion Models for Representation Learning
We introduce SODA, a self-supervised diffusion model, designed for representation learning.
Laser: Latent Set Representations for 3D Generative Modeling
NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint.
Solving Reasoning Tasks with a Slot Transformer
The ability to carve the world into useful abstractions in order to reason about time and space is a crucial component of intelligence.
Object discovery and representation networks
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks.
HiP: Hierarchical Perceiver
This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.
Perceiver IO: A General Architecture for Structured Inputs & Outputs
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015
(Average End-Point Error metric)
SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Leveraging the shared structure that exists across different scenes, our model learns to infer two sets of latent representations from RGB video input alone: a set of "object" latents, corresponding to the time-invariant, object-level contents of the scene, as well as a set of "frame" latents, corresponding to global time-varying elements such as viewpoint.
NeRF-VAE: A Geometry Aware 3D Scene Generative Model
We propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via NeRF and differentiable volume rendering.
PARTS: Unsupervised Segmentation With Slots, Attention and Independence Maximization
We present a model that is able to segment visual scenes from complex 3D environments into distinct objects, learn disentangled representations of individual objects, and form consistent and coherent predictions of future frames, in a fully unsupervised manner.
Towards Robust Image Classification Using Sequential Attention Models
In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception.
Towards Interpretable Reinforcement Learning Using Attention Augmented Agents
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain.
Multi-Object Representation Learning with Iterative Variational Inference
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities.
Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs
In this work, we rigorously test these questions, and find that deformation stability in convolutional networks is more nuanced than it first appears: (1) Deformation invariance is not a binary property, but rather that different tasks require different degrees of deformation stability at different layers.
Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016).
LaVAN: Localized and Visible Adversarial Noise
Most works on adversarial examples for deep-learning based image classifiers use noise that, while small, covers the entire image.
Visual Interaction Networks: Learning a Physics Simulator from Video
We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations.
Variational Memory Addressing in Generative Models
Aiming to augment generative models with external memory, we interpret the output of a memory module with stochastic addressing as a conditional mixture distribution, where a read operation corresponds to sampling a discrete memory address and retrieving the corresponding content from memory.
Visual Interaction Networks
We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems.
Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees
We introduce a new method called differentiable boundary tree which allows for learning deep kNN representations.
Computational Imaging for VLBI Image Reconstruction
Very long baseline interferometry (VLBI) is a technique for imaging celestial radio emissions by simultaneously observing a source from telescopes distributed across Earth.
Learning Ordinal Relationships for Mid-Level Vision
We demonstrate that this frame- work works well on two important mid-level vision tasks: intrinsic image decomposition and depth from an RGB im- age.
Learning visual groups from co-occurrences in space and time
We propose a self-supervised framework that learns to group visual entities based on their rate of co-occurrence in space and time.
Shape and Illumination from Shading using the Generic Viewpoint Assumption
The Generic Viewpoint Assumption (GVA) states that the position of the viewer or the light in a scene is not special.
Learning the Local Statistics of Optical Flow
Motivated by recent progress in natural image statistics, we use newly available datasets with ground truth optical flow to learn the local statistics of optical flow and rigorously compare the learned model to prior models assumed by computer vision optical flow algorithms.
Natural Images, Gaussian Mixtures and Dead Leaves
Simple Gaussian Mixture Models (GMMs) learned from pixels of natural image patches have been recently shown to be surprisingly strong performers in modeling the statistics of natural images.
The 'tree-dependent components' of natural scenes are edge filters
We propose a new model for natural image statistics.
