research
∙
07/07/2022
CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships
As machine learning models become increasingly prevalent in motion forec...
share
research
∙
05/09/2022
When does dough become a bagel? Analyzing the remaining mistakes on ImageNet
Image classification accuracy on the ImageNet dataset has been a baromet...
research
∙
03/10/2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
The conventional recipe for maximizing model accuracy is to (1) train mu...
research
∙
10/06/2021
Spectral Bias in Practice: The Role of Function Frequency in Generalization
Despite their ability to represent highly expressive functions, deep lea...
research
∙
06/30/2021
The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
Although machine learning models typically experience a drop in performa...
research
∙
06/15/2021
Scene Transformer: A unified multi-task model for behavior prediction and planning
Predicting the future motion of multiple agents is necessary for plannin...
research
∙
06/08/2021
AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation
We extend semi-supervised learning to the problem of domain adaptation t...
research
∙
03/02/2021
Pseudo-labeling for Scalable 3D Object Detection
To safely deploy autonomous vehicles, onboard perception systems must wo...
research
∙
12/15/2020
Mitigating bias in calibration error estimation
Building reliable machine learning systems requires that we correctly un...
research
∙
06/05/2019
A systematic framework for natural perturbations from videos
We introduce a systematic framework for quantifying the robustness of cl...
research
∙
06/01/2018
Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Machine learning is currently dominated by largely experimental work foc...
research
∙
05/23/2017
The Marginal Value of Adaptive Gradient Methods in Machine Learning
Adaptive optimization methods, which perform local optimization with a m...
research
∙
02/17/2016