
Revisiting the Calibration of Modern Neural Networks
Accurate estimation of predictive uncertainty (model calibration) is ess...
read it

MLPMixer: An allMLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the goto model for computer vi...
read it

SIScore: An image dataset for finegrained analysis of robustness to object location, rotation and size
Before deploying machine learning models it is critical to assess their ...
read it

ViViT: A Video Vision Transformer
We present puretransformer based models for video classification, drawi...
read it

Underspecification Presents Challenges for Credibility in Modern Machine Learning
ML models often exhibit unexpectedly poor behavior when they are deploye...
read it

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
The idea behind the unsupervised learning of disentangled representation...
read it

Which Model to Transfer? Finding the Needle in the Growing Haystack
Transfer learning has been recently popularized as a dataefficient alte...
read it

Representation learning from videos inthewild: An objectcentric approach
We propose a method to learn image representations from uncurated videos...
read it

A Commentary on the Unsupervised Learning of Disentangled Representations
The goal of the unsupervised learning of disentangled representations is...
read it

On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not g...
read it

SelfSupervised Learning of VideoInduced Visual Invariances
We propose a general framework for selfsupervised learning of transfera...
read it

Semantic Bottleneck Scene Generation
Coupling the highfidelity generation capabilities of labelconditional ...
read it

On Mutual Information Maximization for Representation Learning
Many recent methods for unsupervised or selfsupervised representation l...
read it

Evaluating Generative Models Using Divergence Frontiers
Despite the tremendous progress in the estimation of generative models, ...
read it

HighFidelity Image Generation With Fewer Labels
Deep generative models are becoming a cornerstone of modern machine lear...
read it

Recent Advances in AutoencoderBased Representation Learning
Learning useful representations with little or no supervision is a key c...
read it

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
In recent years, the interest in unsupervised learning of disentangled r...
read it

SelfSupervised Generative Adversarial Networks
Conditional GANs are at the forefront of natural image synthesis. The ma...
read it

On Self Modulation for Generative Adversarial Networks
Training Generative Adversarial Networks (GANs) is notoriously challengi...
read it

The GAN Landscape: Losses, Architectures, Regularization, and Normalization
Generative Adversarial Networks (GANs) are a class of deep generative mo...
read it

Assessing Generative Models via Precision and Recall
Recent advances in generative modeling have led to an increased interest...
read it

Deep Generative Models for DistributionPreserving Lossy Compression
We propose and study the problem of distributionpreserving lossy compre...
read it

Are GANs Created Equal? A LargeScale Study
Generative adversarial networks (GAN) are a powerful subclass of generat...
read it

OneShot Coresets: The Case of kClustering
Scaling clustering algorithms to massive data sets is a challenging task...
read it

Stochastic Submodular Maximization: The Case of Coverage Functions
Stochastic optimization of continuous objectives is at the heart of mode...
read it

Training Mixture Models at Scale via Coresets
How can we train a statistical mixture model on a massive data set? In t...
read it

Practical Coreset Constructions for Machine Learning
We investigate coresets  succinct, small summaries of large data sets ...
read it

Uniform Deviation Bounds for Unbounded Loss Functions like kMeans
Uniform deviation bounds limit the difference between a model's expected...
read it

Scalable and Distributed Clustering via Lightweight Coresets
Coresets are compact representations of data sets such that models train...
read it

Horizontally Scalable Submodular Maximization
A variety of largescale machine learning problems can be cast as instan...
read it

Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning
Faced with massive data, is it possible to trade off (statistical) risk,...
read it

Lineartime Outlier Detection via Sensitivity
Outliers are ubiquitous in modern data sets. Distancebased techniques a...
read it

Strong Coresets for Hard and Soft Bregman Clustering with Applications to Exponential Family Mixtures
Coresets are efficient representations of data sets such that models tra...
read it