Task Agnostic and Post-hoc Unseen Distribution Detection

07/26/2022
by   Radhika Dua, et al.
0

Despite the recent advances in out-of-distribution(OOD) detection, anomaly detection, and uncertainty estimation tasks, there do not exist a task-agnostic and post-hoc approach. To address this limitation, we design a novel clustering-based ensembling method, called Task Agnostic and Post-hoc Unseen Distribution Detection (TAPUDD) that utilizes the features extracted from the model trained on a specific task. Explicitly, it comprises of TAP-Mahalanobis, which clusters the training datasets' features and determines the minimum Mahalanobis distance of the test sample from all clusters. Further, we propose the Ensembling module that aggregates the computation of iterative TAP-Mahalanobis for a different number of clusters to provide reliable and efficient cluster computation. Through extensive experiments on synthetic and real-world datasets, we observe that our approach can detect unseen samples effectively across diverse tasks and performs better or on-par with the existing baselines. To this end, we eliminate the necessity of determining the optimal value of the number of clusters and demonstrate that our method is more viable for large-scale classification tasks.

READ FULL TEXT

page 3

page 4

page 7

page 13

page 15

research
10/15/2022

D.MCA: Outlier Detection with Explicit Micro-Cluster Assignments

How can we detect outliers, both scattered and clustered, and also expli...
research
06/06/2022

Anomaly Detection with Test Time Augmentation and Consistency Evaluation

Deep neural networks are known to be vulnerable to unseen data: they may...
research
10/25/2018

Spectral Embedding Norm: Looking Deep into the Spectrum of the Graph Laplacian

The extraction of clusters from a dataset which includes multiple cluste...
research
12/05/2019

Why Should we Combine Training and Post-Training Methods for Out-of-Distribution Detection?

Deep neural networks are known to achieve superior results in classifica...
research
02/23/2021

CAC: A Clustering Based Framework for Classification

In data containing heterogeneous subpopulations, classification performa...
research
03/24/2023

LINe: Out-of-Distribution Detection by Leveraging Important Neurons

It is important to quantify the uncertainty of input samples, especially...
research
07/30/2020

Stable Learning via Causality-based Feature Rectification

How to learn a stable model under agnostic distribution shift between tr...

Please sign up or login with your details

Forgot password? Click here to reset