Paper Reading AI Learner

Out of distribution robustness with pre-trained Bayesian neural networks

2022-06-24 16:08:46
Xi Wang, Laurence Aitchison
arXiv_AI
   
Abstract

We develop ShiftMatch, a new training-data-dependent likelihood for out of distribution (OOD) robustness in Bayesian neural networks (BNNs). ShiftMatch is inspired by the training-data-dependent "EmpCov" priors from Izmailov et al. (2021a) and efficiently matches test-time spatial correlations to those at training time. Critically, ShiftMatch is designed to leave neural network training unchanged, allowing it to use publically available samples from pretrained BNNs. Using pre-trained HMC samples, ShiftMatch gives strong performance improvements on CIFAR-10-C, outperforms EmpCov priors, and is perhaps the first Bayesian method capable of convincingly outperforming plain deep ensembles. ShiftMatch can be integrated with non-Bayesian methods like deep ensembles, where it offers smaller, but still considerable, performance improvements. Overall, Bayesian ShiftMatch gave slightly better accuracy than ensembles with ShiftMatch, though they both had very similar log-likelihoods.

Abstract (translated)

URL

https://arxiv.org/abs/2206.12361

PDF

https://arxiv.org/pdf/2206.12361.pdf

Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot