Curved Geometric Networks for Visual Anomaly Recognition

08/02/2022
by   Jie Hong, et al.
0

Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature. However, the success of the geometry constraints, posed in the embedding space, indicates that curved spaces might encode more structural information, leading to better discriminative power and hence richer representations. In this work, we investigate benefits of the curved space for analyzing anomalies or out-of-distribution objects in data. This is achieved by considering embeddings via three geometry constraints, namely, spherical geometry (with positive curvature), hyperbolic geometry (with negative curvature) or mixed geometry (with both positive and negative curvatures). Three geometric constraints can be chosen interchangeably in a unified design given the task at hand. Tailored for the embeddings in the curved space, we also formulate functions to compute the anomaly score. Two types of geometric modules (i.e., Geometric-in-One and Geometric-in-Two models) are proposed to plug in the original Euclidean classifier, and anomaly scores are computed from the curved embeddings. We evaluate the resulting designs under a diverse set of visual recognition scenarios, including image detection (multi-class OOD detection and one-class anomaly detection) and segmentation (multi-class anomaly segmentation and one-class anomaly segmentation). The empirical results show the effectiveness of our proposal through the consistent improvement over various scenarios.

READ FULL TEXT

page 1

page 11

research
05/03/2018

Anomaly and Change Detection in Graph Streams through Constant-Curvature Manifold Embeddings

Mapping complex input data into suitable lower dimensional manifolds is ...
research
11/19/2019

Mixed-curvature Variational Autoencoders

It has been shown that using geometric spaces with non-zero curvature in...
research
04/18/2022

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

In large-scale recommender systems, the user-item networks are generally...
research
02/19/2021

Linear Classifiers in Mixed Constant Curvature Spaces

Embedding methods for mixed-curvature spaces are powerful techniques for...
research
07/31/2023

L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space

The performance of a lifelong learning (L3) model degrades when it is tr...
research
08/16/2018

How did the shape of your network change? (On detecting anomalies in static and dynamic networks via change of non-local curvatures)

Notions of local and non-local curvatures of higher-dimensional geometri...
research
09/02/2008

From Data to the p-Adic or Ultrametric Model

We model anomaly and change in data by embedding the data in an ultramet...

Please sign up or login with your details

Forgot password? Click here to reset