Conditional Permutation Invariant Flows

06/17/2022
by   Berend Zwartsenberg, et al.
2

We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density. This model is a continuous normalizing flow governed by permutation equivariant dynamics. These dynamics are driven by a learnable per-set-element term and pairwise interactions, both parametrized by deep neural networks. We illustrate the utility of this model via applications including (1) complex traffic scene generation conditioned on visually specified map information, and (2) object bounding box generation conditioned directly on images. We train our model by maximizing the expected likelihood of labeled conditional data under our flow, with the aid of a penalty that ensures the dynamics are smooth and hence efficiently solvable. Our method significantly outperforms non-permutation invariant baselines in terms of log likelihood and domain-specific metrics (offroad, collision, and combined infractions), yielding realistic samples that are difficult to distinguish from real data.

READ FULL TEXT

page 2

page 8

page 9

page 17

page 19

page 20

research
09/06/2019

Set Flow: A Permutation Invariant Normalizing Flow

We present a generative model that is defined on finite sets of exchange...
research
08/04/2019

Probabilistic Permutation Invariant Training for Speech Separation

Single-microphone, speaker-independent speech separation is normally per...
research
05/19/2021

E(n) Equivariant Normalizing Flows for Molecule Generation in 3D

This paper introduces a generative model equivariant to Euclidean symmet...
research
06/07/2023

Multiscale Flow for Robust and Optimal Cosmological Analysis

We propose Multiscale Flow, a generative Normalizing Flow that creates s...
research
12/17/2019

HCNAF: Hyper-Conditioned Neural Autoregressive Flow and its Application for Probabilistic Occupancy Map Forecasting

We introduce Hyper-Conditioned Neural Autoregressive Flow (HCNAF); a pow...
research
02/21/2018

A Generative Deep Recurrent Model for Exchangeable Data

We present a novel model architecture which leverages deep learning tool...

Please sign up or login with your details

Forgot password? Click here to reset