research
∙
02/20/2023
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Adversarial training is widely used to make classifiers robust to a spec...
share
research
∙
09/30/2022
Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods
Self-supervised methods have achieved remarkable success in transfer lea...
research
∙
07/07/2022
Back to the Source: Diffusion-Driven Test-Time Adaptation
Test-time adaptation harnesses test inputs to improve the accuracy of a ...
research
∙
03/16/2022
Object discovery and representation networks
The promise of self-supervised learning (SSL) is to leverage large amoun...
research
∙
02/28/2022
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
Adaptive defenses that use test-time optimization promise to improve rob...
research
∙
02/22/2022
Hierarchical Perceiver
General perception systems such as Perceivers can process arbitrary moda...
research
∙
09/02/2021
On-target Adaptation
Domain adaptation seeks to mitigate the shift between training on the so...
research
∙
07/30/2021
Perceiver IO: A General Architecture for Structured Inputs Outputs
The recently-proposed Perceiver model obtains good results on several do...
research
∙
05/18/2021
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
Adversarial attacks optimize against models to defeat defenses. Existing...
research
∙
04/01/2021
Confidence Adaptive Anytime Pixel-Level Recognition
Anytime inference requires a model to make a progression of predictions ...
research
∙
07/12/2020
It Is Likely That Your Loss Should be a Likelihood
We recall that certain common losses are simplified likelihoods and inst...
research
∙
06/18/2020
Fully Test-time Adaptation by Entropy Minimization
Faced with new and different data during testing, a model must adapt its...
research
∙
08/08/2019
Dynamic Scale Inference by Entropy Minimization
Given the variety of the visual world there is not one true scale for re...
research
∙
04/25/2019
Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields
The visual world is vast and varied, but its variations divide into stru...
research
∙
02/12/2019
Infinite Mixture Prototypes for Few-Shot Learning
We propose infinite mixture prototypes to adaptively represent both simp...
research
∙
04/23/2018
Zero-Shot Visual Imitation
The current dominant paradigm for imitation learning relies on strong su...
research
∙
08/11/2016
Clockwork Convnets for Video Semantic Segmentation
Recent years have seen tremendous progress in still-image segmentation; ...
research
∙
05/20/2016
Fully Convolutional Networks for Semantic Segmentation
Convolutional networks are powerful visual models that yield hierarchies...
research
∙
12/22/2014
Fully Convolutional Multi-Class Multiple Instance Learning
Multiple instance learning (MIL) can reduce the need for costly annotati...
research
∙
06/20/2014