546 citations · 1.4k across the 15 of their papers we have counts for
16 papers
Multi-Agent Reachability Calibration with Conformal Prediction
Anish Muthali, Haotian Shen, Sampada Deglurkar +4
We investigate methods to provide safety assurances for autonomous agents that incorporate predictions of other, uncontrolled agents' behavior into their own trajectory planning. G…
CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships
Rebecca Roelofs, Liting Sun, Ben Caine +4
As machine learning models become increasingly prevalent in motion forecasting for autonomous vehicles (AVs), it is critical to ensure that model predictions are safe and reliable.…
When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
Vijay Vasudevan, Benjamin Caine, Raphael Gontijo-Lopes +2
Image classification accuracy on the ImageNet dataset has been a barometer for progress in computer vision over the last decade. Several recent papers have questioned the degree to…
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre +8
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-o…
Spectral Bias in Practice: The Role of Function Frequency in Generalization
Sara Fridovich-Keil, Raphael Gontijo-Lopes, Rebecca Roelofs
Despite their ability to represent highly expressive functions, deep learning models seem to find simple solutions that generalize surprisingly well. Spectral bias -- the tendency…
Robust fine-tuning of zero-shot models
Mitchell Wortsman, Gabriel Ilharco, Jong Wook Kim +8
Large pre-trained models such as CLIP or ALIGN offer consistent accuracy across a range of data distributions when performing zero-shot inference (i.e., without fine-tuning on a sp…
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
Anders Andreassen, Yasaman Bahri, Behnam Neyshabur +1
Although machine learning models typically experience a drop in performance on out-of-distribution data, accuracies on in- versus out-of-distribution data are widely observed to fo…
Scene Transformer: A unified architecture for predicting multiple agent trajectories
Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan +11
Predicting the motion of multiple agents is necessary for planning in dynamic environments. This task is challenging for autonomous driving since agents (e.g. vehicles and pedestri…
AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation
David Berthelot, Rebecca Roelofs, Kihyuk Sohn +2
We extend semi-supervised learning to the problem of domain adaptation to learn significantly higher-accuracy models that train on one data distribution and test on a different one…
Pseudo-labeling for Scalable 3D Object Detection
Benjamin Caine, Rebecca Roelofs, Vijay Vasudevan +4
To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common te…
Mitigating Bias in Calibration Error Estimation
Rebecca Roelofs, Nicholas Cain, Jonathon Shlens +1
For an AI system to be reliable, the confidence it expresses in its decisions must match its accuracy. To assess the degree of match, examples are typically binned by confidence an…
Do Image Classifiers Generalize Across Time?
Vaishaal Shankar, Achal Dave, Rebecca Roelofs +3
We study the robustness of image classifiers to temporal perturbations derived from videos. As part of this study, we construct two datasets, ImageNet-Vid-Robust and YTBB-Robust ,…
Do ImageNet Classifiers Generalize to ImageNet?
Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt +1
We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to exc…
Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt +1
Machine learning is currently dominated by largely experimental work focused on improvements in a few key tasks. However, the impressive accuracy numbers of the best performing mod…
The Marginal Value of Adaptive Gradient Methods in Machine Learning
Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern +2
Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural n…
Large Scale Kernel Learning using Block Coordinate Descent
Stephen Tu, Rebecca Roelofs, Shivaram Venkataraman +1
We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points. Armed with this capability, w…