Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding

About

Normalizing flow-based generative models have been widely used in applications where the exact density estimation is of major importance. Recent research proposes numerous methods to improve their expressivity. However, conditioning on a context is largely overlooked area in the bijective flow research. Conventional conditioning with the vector concatenation is limited to only a few flow types. More importantly, this approach cannot support a practical setup where a set of context-conditioned (specialist) models are trained with the fixed pretrained general-knowledge (generalist) model. We propose ContextFlow++ approach to overcome these limitations using an additive conditioning with explicit generalist-specialist knowledge decoupling. Furthermore, we support discrete contexts by the proposed mixed-variable architecture with context encoders. Particularly, our context encoder for discrete variables is a surjective flow from which the context-conditioned continuous variables are sampled. Our experiments on rotated MNIST-R, corrupted CIFAR-10C, real-world ATM predictive maintenance and SMAP unsupervised anomaly detection benchmarks show that the proposed ContextFlow++ offers faster stable training and achieves higher performance metrics. Our code is publicly available at https://github.com/gudovskiy/contextflow.

Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata• 2024

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-10-C (test)
Accuracy (Clean)57.7
61
Anomaly DetectionSMAP (test)
Precision88.64
37
Image ClassificationMNIST-R 64 rotations (test)
Top-1 Accuracy97.9
14
Time series failure predictionReal-world ATM machine failure prediction (modified splits)
Accuracy98.5
8
Showing 4 of 4 rows

Other info

Code

Follow for update