DeepAI AI Chat
Log In Sign Up

Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity

11/28/2022
by   Nathan Drenkow, et al.
0

The deployment of machine learning models in safety-critical applications comes with the expectation that such models will perform well over a range of contexts (e.g., a vision model for classifying street signs should work in rural, city, and highway settings under varying lighting/weather conditions). However, these one-size-fits-all models are typically optimized for average case performance, encouraging them to achieve high performance in nominal conditions but exposing them to unexpected behavior in challenging or rare contexts. To address this concern, we develop a new method for training context-dependent models. We extend Bridge-Mode Connectivity (BMC) (Garipov et al., 2018) to train an infinite ensemble of models over a continuous measure of context such that we can sample model parameters specifically tuned to the corresponding evaluation context. We explore the definition of context in image classification tasks through multiple lenses including changes in the risk profile, long-tail image statistics/appearance, and context-dependent distribution shift. We develop novel extensions of the BMC optimization for each of these cases and our experiments demonstrate that model performance can be successfully tuned to context in each scenario.

READ FULL TEXT

page 7

page 8

12/01/2021

Robustness in Deep Learning for Computer Vision: Mind the gap?

Deep neural networks for computer vision tasks are deployed in increasin...
08/24/2020

Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems

Learning-based methodologies increasingly find applications in safety-cr...
11/02/2022

Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese

The tremendous success of CLIP (Radford et al., 2021) has promoted the r...
03/02/2020

Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method

Long-tail and rare event problems become crucial when autonomous driving...
12/12/2018

Can I trust you more? Model-Agnostic Hierarchical Explanations

Interactions such as double negation in sentences and scene interactions...