Search Results for author:
Found 17 papers, 12 papers with code
Understanding Contrastive Representation Learning through Geometry on the Hypersphere
Contrastive representation learning has been outstandingly successful in practice.
Deep Augmentation: Enhancing Self-Supervised Learning through Transformations in Higher Activation Space
We introduce Deep Augmentation, an approach to data augmentation using dropout to dynamically transform a targeted layer within a neural network, with the option to use the stop-gradient operation, offering significant improvements in model performance and generalization.
Steerable Equivariant Representation Learning
In this paper, we propose a method of learning representations that are instead equivariant to data augmentations.
Procedural Image Programs for Representation Learning
Learning image representations using synthetic data allows training neural networks without some of the concerns associated with real images, such as privacy and bias.
Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications.
Totems: Physical Objects for Verifying Visual Integrity
We introduce a new approach to image forensics: placing physical refractive objects, which we call totems, into a scene so as to protect any photograph taken of that scene.
Denoised MDPs: Learning World Models Better Than the World Itself
The ability to separate signal from noise, and reason with clean abstractions, is critical to intelligence.
On the Learning and Learnability of Quasimetrics
In contrast, our proposed Poisson Quasimetric Embedding (PQE) is the first quasimetric learning formulation that both is learnable with gradient-based optimization and enjoys strong performance guarantees.
Dataset Distillation by Matching Training Trajectories
To efficiently obtain the initial and target network parameters for large-scale datasets, we pre-compute and store training trajectories of expert networks trained on the real dataset.
Learning to See by Looking at Noise
We investigate a suite of image generation models that produce images from simple random processes.
Rewriting a Deep Generative Model
To address the problem, we propose a formulation in which the desired rule is changed by manipulating a layer of a deep network as a linear associative memory.
Diverse Image Generation via Self-Conditioned GANs
We introduce a simple but effective unsupervised method for generating realistic and diverse images.
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
Contrastive representation learning has been outstandingly successful in practice.
Dataset Distillation
Model distillation aims to distill the knowledge of a complex model into a simpler one.
Meta-Learning MCMC Proposals
The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required.
Learning to Synthesize a 4D RGBD Light Field from a Single Image
We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction).
