Search Results for author:
Found 23 papers, 11 papers with code
LAVAE: Disentangling Location and Appearance
We propose a probabilistic generative model for unsupervised learning of structured, interpretable, object-based representations of visual scenes.
Semi-Supervised Variational Autoencoder for Survival Prediction
In this paper we propose a semi-supervised variational autoencoder for classification of overall survival groups from tumor segmentation masks.
Towards Hierarchical Discrete Variational Autoencoders
We introduce the Hierarchical Discrete Variational Autoencoder (HD-VAE): a hi- erarchy of variational memory layers.
On Disentangled Representations Learned From Correlated Data
The focus of disentanglement approaches has been on identifying independent factors of variation in data.
Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE).
On the Transfer of Disentangled Representations in Realistic Settings
Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning.
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds
Empirically, for the training of both continuous and discrete generative models, the proposed method yields superior variance reduction, resulting in an SNR for IWAE that increases with $K$ without relying on the reparameterization trick.
Planning from Pixels in Atari with Learned Symbolic Representations
Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input.
Full-Body Motion From a Single Head-Mounted Device: Generating SMPL Poses From Partial Observations
The increased availability and maturity of head-mounted and wearable devices opens up opportunities for remote communication and collaboration.
Representation Learning for Out-of-distribution Generalization in Reinforcement Learning
Learning data representations that are useful for various downstream tasks is a cornerstone of artificial intelligence.
Out-of-Distribution Generalization
reinforcement-learning
+2
Generalization and Robustness Implications in Object-Centric Learning
The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations.
The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
By training 240 representations and over 10, 000 reinforcement learning (RL) policies on a simulated robotic setup, we evaluate to what extent different properties of pretrained VAE-based representations affect the OOD generalization of downstream agents.
Boxhead: A Dataset for Learning Hierarchical Representations
Disentanglement is hypothesized to be beneficial towards a number of downstream tasks.
Conditional Generation of Medical Time Series for Extrapolation to Underrepresented Populations
We demonstrate experimentally that HealthGen generates synthetic cohorts that are significantly more faithful to real patient EHRs than the current state-of-the-art, and that augmenting real data sets with conditionally generated cohorts of underrepresented subpopulations of patients can significantly enhance the generalisability of models derived from these data sets to different patient populations.
Image Super-Resolution With Deep Variational Autoencoders
Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image.
Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging.
Diffusion Models for Video Prediction and Infilling
By varying the mask we condition on, the model is able to perform video prediction, infilling, and upsampling.
Ranked #2 on
Video Generation
on BAIR Robot Pushing
Assaying Out-Of-Distribution Generalization in Transfer Learning
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e. g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations.
Adversarial Robustness
Out-of-Distribution Generalization
+1
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation.
Assessing Neural Network Robustness via Adversarial Pivotal Tuning
We demonstrate that APT is capable of a wide range of class-preserving semantic image manipulations that fool a variety of pretrained classifiers.
On the Generalization of Learned Structured Representations
In representation learning, large datasets are leveraged to learn generic data representations that may be useful for efficient learning of arbitrary downstream tasks.
Out-of-Distribution Generalization
Representation Learning
+1
DiffEnc: Variational Diffusion with a Learned Encoder
Diffusion models may be viewed as hierarchical variational autoencoders (VAEs) with two improvements: parameter sharing for the conditional distributions in the generative process and efficient computation of the loss as independent terms over the hierarchy.
Diffusion Based Causal Representation Learning
Causal reasoning can be considered a cornerstone of intelligent systems.
