Search Results for author:
Found 25 papers, 13 papers with code
Flare Prediction Using Photospheric and Coronal Image Data
This is the first attempt to predict solar flares using photospheric vector magnetic field data as well as multiple wavelengths of image data from the chromosphere, transition region, and corona.
Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Although we ensure that the new test set is as close to the original data distribution as possible, we find a large drop in accuracy (4% to 10%) for a broad range of deep learning models.
Cloud Programming Simplified: A Berkeley View on Serverless Computing
Serverless cloud computing handles virtually all the system administration operations needed to make it easier for programmers to use the cloud.
Operating Systems
Do ImageNet Classifiers Generalize to ImageNet?
We evaluate a broad range of models and find accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet.
A Systematic Framework for Natural Perturbations from Videos
We introduce a systematic framework for quantifying the robustness of classifiers to naturally occurring perturbations of images found in videos.
Do Image Classifiers Generalize Across Time?
Additionally, we evaluate three detection models and show that natural perturbations induce both classification as well as localization errors, leading to a median drop in detection mAP of 14 points.
When Robustness Doesn’t Promote Robustness: Synthetic vs. Natural Distribution Shifts on ImageNet
We conduct a large experimental comparison of various robustness metrics for image classification.
A Meta-Analysis of Overfitting in Machine Learning
By systematically comparing the public ranking with the final ranking, we assess how much participants adapted to the holdout set over the course of a competition.
Serverless Straggler Mitigation using Local Error-Correcting Codes
Inexpensive cloud services, such as serverless computing, are often vulnerable to straggling nodes that increase end-to-end latency for distributed computation.
Distributed, Parallel, and Cluster Computing Information Theory Information Theory
Neural Kernels Without Tangents
We investigate the connections between neural networks and simple building blocks in kernel space.
Measuring Robustness to Natural Distribution Shifts in Image Classification
We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets.
Ranked #41 on
Domain Generalization
on VizWiz-Classification
A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use.
Predicting with Confidence on Unseen Distributions
Our work connects techniques from domain adaptation and predictive uncertainty literature, and allows us to predict model accuracy on challenging unseen distributions without access to labeled data.
Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
For machine learning systems to be reliable, we must understand their performance in unseen, out-of-distribution environments.
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
Contrastively trained language-image models such as CLIP, ALIGN, and BASIC have demonstrated unprecedented robustness to multiple challenging natural distribution shifts.
Ranked #94 on
Image Classification
on ObjectNet
(using extra training data)
Masked Autoencoding Does Not Help Natural Language Supervision at Scale
Self supervision and natural language supervision have emerged as two exciting ways to train general purpose image encoders which excel at a variety of downstream tasks.
On Robustness in Multimodal Learning
Multimodal learning is defined as learning over multiple heterogeneous input modalities such as video, audio, and text.
DataComp: In search of the next generation of multimodal datasets
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms.
Data Filtering Networks
Our key finding is that the quality of a network for filtering is distinct from its performance on downstream tasks: for instance, a model that performs well on ImageNet can yield worse training sets than a model with low ImageNet accuracy that is trained on a small amount of high-quality data.
Robust multimodal models have outlier features and encode more concepts
In this work, we bridge this gap by probing the representation spaces of 12 robust multimodal models with various backbones (ResNets and ViTs) and pretraining sets (OpenAI, LAION-400M, LAION-2B, YFCC15M, CC12M and DataComp).
TiC-CLIP: Continual Training of CLIP Models
We introduce the first set of web-scale Time-Continual (TiC) benchmarks for training vision-language models: TiC-DataComp, TiC-YFCC, and TiC-Redcaps.
Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation
Recent advances in image tokenizers, such as VQ-VAE, have enabled text-to-image generation using auto-regressive methods, similar to language modeling.
Scalable Pre-training of Large Autoregressive Image Models
Specifically, we highlight two key findings: (1) the performance of the visual features scale with both the model capacity and the quantity of data, (2) the value of the objective function correlates with the performance of the model on downstream tasks.
Ranked #333 on
Image Classification
on ImageNet
(using extra training data)
Language models scale reliably with over-training and on downstream tasks
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
Evaluating Machine Accuracy on ImageNet
We perform an in-depth evaluation of human accuracy on the ImageNet dataset.
