research
∙
07/12/2023
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
The ubiquitous and demonstrably suboptimal choice of resizing images to ...
share
research
∙
04/24/2023
End-to-End Spatio-Temporal Action Localisation with Video Transformers
The most performant spatio-temporal action localisation models use exter...
research
∙
12/09/2022
Audiovisual Masked Autoencoders
Can we leverage the audiovisual information already present in video to ...
research
∙
07/08/2022
Beyond Transfer Learning: Co-finetuning for Action Localisation
Transfer learning is the predominant paradigm for training deep networks...
research
∙
06/15/2022
VCT: A Video Compression Transformer
We show how transformers can be used to vastly simplify neural video com...
research
∙
11/25/2021
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
A classical problem in computer vision is to infer a 3D scene representa...
research
∙
11/25/2021
PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Can we train a single transformer model capable of processing multiple m...
research
∙
06/15/2021
Revisiting the Calibration of Modern Neural Networks
Accurate estimation of predictive uncertainty (model calibration) is ess...
research
∙
05/04/2021
MLP-Mixer: An all-MLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the go-to model for computer vi...
research
∙
04/09/2021
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size
Before deploying machine learning models it is critical to assess their ...
research
∙
03/29/2021
ViViT: A Video Vision Transformer
We present pure-transformer based models for video classification, drawi...
research
∙
11/06/2020
Underspecification Presents Challenges for Credibility in Modern Machine Learning
ML models often exhibit unexpectedly poor behavior when they are deploye...
research
∙
10/27/2020
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
The idea behind the unsupervised learning of disentangled representation...
research
∙
10/13/2020
Which Model to Transfer? Finding the Needle in the Growing Haystack
Transfer learning has been recently popularized as a data-efficient alte...
research
∙
10/06/2020
Representation learning from videos in-the-wild: An object-centric approach
We propose a method to learn image representations from uncurated videos...
research
∙
07/28/2020
A Commentary on the Unsupervised Learning of Disentangled Representations
The goal of the unsupervised learning of disentangled representations is...
research
∙
07/16/2020
On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not g...
research
∙
12/05/2019
Self-Supervised Learning of Video-Induced Visual Invariances
We propose a general framework for self-supervised learning of transfera...
research
∙
11/26/2019
Semantic Bottleneck Scene Generation
Coupling the high-fidelity generation capabilities of label-conditional ...
research
∙
07/31/2019
On Mutual Information Maximization for Representation Learning
Many recent methods for unsupervised or self-supervised representation l...
research
∙
05/26/2019
Evaluating Generative Models Using Divergence Frontiers
Despite the tremendous progress in the estimation of generative models, ...
research
∙
03/06/2019
High-Fidelity Image Generation With Fewer Labels
Deep generative models are becoming a cornerstone of modern machine lear...
research
∙
12/12/2018
Recent Advances in Autoencoder-Based Representation Learning
Learning useful representations with little or no supervision is a key c...
research
∙
11/29/2018
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
In recent years, the interest in unsupervised learning of disentangled r...
research
∙
11/27/2018
Self-Supervised Generative Adversarial Networks
Conditional GANs are at the forefront of natural image synthesis. The ma...
research
∙
10/02/2018
On Self Modulation for Generative Adversarial Networks
Training Generative Adversarial Networks (GANs) is notoriously challengi...
research
∙
07/12/2018
The GAN Landscape: Losses, Architectures, Regularization, and Normalization
Generative Adversarial Networks (GANs) are a class of deep generative mo...
research
∙
05/31/2018
Assessing Generative Models via Precision and Recall
Recent advances in generative modeling have led to an increased interest...
research
∙
05/28/2018
Deep Generative Models for Distribution-Preserving Lossy Compression
We propose and study the problem of distribution-preserving lossy compre...
research
∙
11/28/2017
Are GANs Created Equal? A Large-Scale Study
Generative adversarial networks (GAN) are a powerful subclass of generat...
research
∙
11/27/2017
One-Shot Coresets: The Case of k-Clustering
Scaling clustering algorithms to massive data sets is a challenging task...
research
∙
11/05/2017
Stochastic Submodular Maximization: The Case of Coverage Functions
Stochastic optimization of continuous objectives is at the heart of mode...
research
∙
03/23/2017
Training Mixture Models at Scale via Coresets
How can we train a statistical mixture model on a massive data set? In t...
research
∙
03/19/2017
Practical Coreset Constructions for Machine Learning
We investigate coresets - succinct, small summaries of large data sets -...
research
∙
02/27/2017
Uniform Deviation Bounds for Unbounded Loss Functions like k-Means
Uniform deviation bounds limit the difference between a model's expected...
research
∙
02/27/2017
Scalable and Distributed Clustering via Lightweight Coresets
Coresets are compact representations of data sets such that models train...
research
∙
05/31/2016
Horizontally Scalable Submodular Maximization
A variety of large-scale machine learning problems can be cast as instan...
research
∙
05/02/2016
Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning
Faced with massive data, is it possible to trade off (statistical) risk,...
research
∙
05/02/2016
Linear-time Outlier Detection via Sensitivity
Outliers are ubiquitous in modern data sets. Distance-based techniques a...
research
∙
08/21/2015