Search Results for author:
Found 35 papers, 18 papers with code
Learning Vision from Models Rivals Learning Vision from Data
We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data.
The Limits of Fair Medical Imaging AI In The Wild
As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities.
Scaling Laws of Synthetic Images for Model Training ... for Now
Our findings also suggest that scaling synthetic data can be particularly effective in scenarios such as: (1) when there is a limited supply of real images for a supervised problem (e. g., fewer than 0. 5 million images in ImageNet), (2) when the evaluation dataset diverges significantly from the training data, indicating the out-of-distribution scenario, or (3) when synthetic data is used in conjunction with real images, as demonstrated in the training of CLIP models.
Return of Unconditional Generation: A Self-supervised Representation Generation Method
This gap can be attributed to the lack of semantic information provided by labels.
Ranked #1 on
Unconditional Image Generation
on ImageNet 256x256
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
We demonstrate image generation and captioning performance on par with state-of-the-art text-to-image and image-to-text models with orders of magnitude fewer (only 3M) paired image-text data.
Unsupervised Object Localization with Representer Point Selection
We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning.
Improving CLIP Training with Language Rewrites
During training, LaCLIP randomly selects either the original texts or the rewritten versions as text augmentations for each image.
Reparo: Loss-Resilient Generative Codec for Video Conferencing
Packet loss during video conferencing often leads to poor quality and video freezing.
Change is Hard: A Closer Look at Subpopulation Shift
Machine learning models often perform poorly on subgroups that are underrepresented in the training data.
Contactless Oxygen Monitoring with Gated Transformer
With the increasing popularity of telehealth, it becomes critical to ensure that basic physiological signals can be monitored accurately at home, with minimal patient overhead.
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
In this work, we propose MAsked Generative Encoder (MAGE), the first framework to unify SOTA image generation and self-supervised representation learning.
Ranked #2 on
Unconditional Image Generation
on ImageNet 256x256
SimPer: Simple Self-Supervised Learning of Periodic Targets
From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes.
Unsupervised Learning for Human Sensing Using Radio Signals
Thus, in this paper, we explore the feasibility of adapting RGB-based unsupervised representation learning to RF signals.
On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond
We first develop the domain-class transferability graph, and show that such transferability governs the success of learning in MDLT.
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
We propose Contrastive Poisoning (CP), the first effective such attack on CL.
Unsupervised Domain Generalization by Learning a Bridge Across Domains
The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system.
Targeted Supervised Contrastive Learning for Long-Tailed Recognition
This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data.
Ranked #22 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Delving into Deep Imbalanced Regression
We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range.
Learning Blood Oxygen from Respiration Signals
Further, since breathing can be monitored without body contact by analyzing the radio signal in the environment, we show that oxygen too can be monitored without any wearable devices.
Addressing Feature Suppression in Unsupervised Visual Representations
However, contrastive learning is susceptible to feature suppression, i. e., it may discard important information relevant to the task of interest, and learn irrelevant features.
In-Home Daily-Life Captioning Using Radio Signals
This paper aims to caption daily life --i. e., to create a textual description of people's activities and interactions with objects in their homes.
Continuously Indexed Domain Adaptation
Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.
Ranked #1 on
Domain Adaptation
on Rotating MNIST
Continuously Index Domain Adaptation
Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.
Self-Supervised Learning of Appliance Usage
We show that this cross-modal prediction task allows us to detect when a particular appliance is used, and the location of the appliance in the home, all in a self-supervised manner, without any labeled data.
Learning Longterm Representations for Person Re-Identification Using Radio Signals
RF signals traverse clothes and reflect off the human body; thus they can be used to extract more persistent human-identifying features like body size and shape.
Learning Compositional Koopman Operators for Model-Based Control
Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis.
Harnessing Structures for Value-Based Planning and Reinforcement Learning
In this paper, we propose to exploit the underlying structures of the state-action value function, i. e., Q function, for both planning and deep RL.
Making the Invisible Visible: Action Recognition Through Walls and Occlusions
Understanding people's actions and interactions typically depends on seeing them.
Ranked #1 on
RF-based Pose Estimation
on RF-MMD
ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation
We show that this process destroys the adversarial structure of the noise, while re-enforcing the global structure in the original image.
Learning-Based Frequency Estimation Algorithms
Estimating the frequencies of elements in a data stream is a fundamental task in data analysis and machine learning.
Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
We consider the problem of inferring the values of an arbitrary set of variables (e. g., risk of diseases) given other observed variables (e. g., symptoms and diagnosed diseases) and high-dimensional signals (e. g., MRI images or EEG).
RF-Based Fall Monitoring Using Convolutional Neural Networks
Falls are the top reason for fatal and non-fatal injuries among seniors.
Ranked #2 on
RF-based Pose Estimation
on RF-MMD
RF-based 3D skeletons
It maintains this accuracy even in the presence of multiple people, and in new environments that it has not seen in the training set.
Through-Wall Human Pose Estimation Using Radio Signals
Yet, unlike vision-based pose estimation, the radio-based system can estimate 2D poses through walls despite never trained on such scenarios.
Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture
We focus on predicting sleep stages from radio measurements without any attached sensors on subjects.
