Search Results for author:
Found 46 papers, 23 papers with code
Subspace clustering of dimensionality-reduced data
Subspace clustering refers to the problem of clustering unlabeled high-dimensional data points into a union of low-dimensional linear subspaces, assumed unknown.
Nonparametric Nearest Neighbor Random Process Clustering
We consider the problem of clustering noisy finite-length observations of stationary ergodic random processes according to their nonparametric generative models without prior knowledge of the model statistics and the number of generative models.
Dimensionality-reduced subspace clustering
Subspace clustering refers to the problem of clustering unlabeled high-dimensional data points into a union of low-dimensional linear subspaces, whose number, orientations, and dimensions are all unknown.
Pursuits in Structured Non-Convex Matrix Factorizations
Efficiently representing real world data in a succinct and parsimonious manner is of central importance in many fields.
Discrete Deep Feature Extraction: A Theory and New Architectures
First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and B\"olcskei, 2015.
Deep Structured Features for Semantic Segmentation
We propose a highly structured neural network architecture for semantic segmentation with an extremely small model size, suitable for low-power embedded and mobile platforms.
Robust nonparametric nearest neighbor random process clustering
We consider the problem of clustering noisy finite-length observations of stationary ergodic random processes according to their generative models without prior knowledge of the model statistics and the number of generative models.
Noisy subspace clustering via matching pursuits
The clustering conditions we obtain for SSC-OMP and SSC-MP are similar to those for SSC and for the thresholding-based subspace clustering (TSC) algorithm due to Heckel and B\"olcskei.
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms.
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy.
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Greedy optimization methods such as Matching Pursuit (MP) and Frank-Wolfe (FW) algorithms regained popularity in recent years due to their simplicity, effectiveness and theoretical guarantees.
Convolutional Recurrent Neural Networks for Electrocardiogram Classification
We propose two deep neural network architectures for classification of arbitrary-length electrocardiogram (ECG) recordings and evaluate them on the atrial fibrillation (AF) classification data set provided by the PhysioNet/CinC Challenge 2017.
StrassenNets: Deep Learning with a Multiplication Budget
A large fraction of the arithmetic operations required to evaluate deep neural networks (DNNs) consists of matrix multiplications, in both convolution and fully connected layers.
Conditional Probability Models for Deep Image Compression
During training, the auto-encoder makes use of the context model to estimate the entropy of its representation, and the context model is concurrently updated to learn the dependencies between the symbols in the latent representation.
Towards Image Understanding from Deep Compression without Decoding
Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as classification and segmentation directly on the compressed representations produced by these compression methods.
Generative Adversarial Networks for Extreme Learned Image Compression
We present a learned image compression system based on GANs, operating at extremely low bitrates.
Born Again Neural Networks
Knowledge distillation (KD) consists of transferring knowledge from one machine learning model (the teacher}) to another (the student).
Deep Generative Models for Distribution-Preserving Lossy Compression
We propose and study the problem of distribution-preserving lossy compression.
Practical Full Resolution Learned Lossless Image Compression
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000.
Ranked #3 on
Image Compression
on ImageNet32
Recent Advances in Autoencoder-Based Representation Learning
Finally, we provide an analysis of autoencoder-based representation learning through the lens of rate-distortion theory and identify a clear tradeoff between the amount of prior knowledge available about the downstream tasks, and how useful the representation is for this task.
High-Fidelity Image Generation With Fewer Labels
Deep generative models are becoming a cornerstone of modern machine learning.
Ranked #10 on
Conditional Image Generation
on ImageNet 128x128
Conditional Image Generation
Vocal Bursts Intensity Prediction
Disentangling Factors of Variation Using Few Labels
Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations.
On Mutual Information Maximization for Representation Learning
Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data.
The Visual Task Adaptation Benchmark
Representation learning promises to unlock deep learning for the long tail of vision tasks without expansive labelled datasets.
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
And, how close are we to general visual representations?
Ranked #10 on
Image Classification
on VTAB-1k
(using extra training data)
Semantic Bottleneck Scene Generation
For the former, we use an unconditional progressive segmentation generation network that captures the distribution of realistic semantic scene layouts.
Ranked #1 on
Image Generation
on Cityscapes-5K 256x512
Self-Supervised Learning of Video-Induced Visual Invariances
We propose a general framework for self-supervised learning of transferable visual representations based on Video-Induced Visual Invariances (VIVI).
Ranked #15 on
Image Classification
on VTAB-1k
(using extra training data)
Weakly-Supervised Disentanglement Without Compromises
Third, we perform a large-scale empirical study and show that such pairs of observations are sufficient to reliably learn disentangled representations on several benchmark data sets.
Automatic Shortcut Removal for Self-Supervised Representation Learning
In self-supervised visual representation learning, a feature extractor is trained on a "pretext task" for which labels can be generated cheaply, without human annotation.
Learning Better Lossless Compression Using Lossy Compression
We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system.
Disentangling Factors of Variations Using Few Labels
Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations.
High-Fidelity Generative Image Compression
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system.
On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts.
Representation learning from videos in-the-wild: An object-centric approach
We propose a method to learn image representations from uncurated videos.
Unconditional Synthesis of Complex Scenes Using a Semantic Bottleneck
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex scenes.
Neural Face Video Compression using Multiple Views
Recent advances in deep generative models led to the development of neural face video compression codecs that use an order of magnitude less bandwidth than engineered codecs.
CLIPPO: Image-and-Language Understanding from Pixels Only
Multimodal models are becoming increasingly effective, in part due to unified components, such as the Transformer architecture.
FlexiViT: One Model for All Patch Sizes
Vision Transformers convert images to sequences by slicing them into patches.
Scaling Vision Transformers to 22 Billion Parameters
The scaling of Transformers has driven breakthrough capabilities for language models.
Ranked #1 on
Zero-Shot Transfer Image Classification
on ObjectNet
M2T: Masking Transformers Twice for Faster Decoding
We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results.
PaLI-X: On Scaling up a Multilingual Vision and Language Model
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture.
Ranked #1 on
Fine-Grained Image Recognition
on OVEN
Image Captioners Are Scalable Vision Learners Too
We further analyze the effect of the model architecture and scale, as well as the pretraining data on the representation quality, and find that captioning exhibits the same or better scaling behavior along these axes.
Finite Scalar Quantization: VQ-VAE Made Simple
Each dimension is quantized to a small set of fixed values, leading to an (implicit) codebook given by the product of these sets.
GIVT: Generative Infinite-Vocabulary Transformers
We introduce generative infinite-vocabulary transformers (GIVT) which generate vector sequences with real-valued entries, instead of discrete tokens from a finite vocabulary.
Ranked #13 on
Image Generation
on ImageNet 256x256
Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers
Recently, these models achieved great performance on tasks such as compositional visual question answering, visual grounding, and video temporal reasoning.
LocCa: Visual Pretraining with Location-aware Captioners
In this paper, we propose a simple visual pretraining method with location-aware captioners (LocCa).
