Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?

05/19/2021
by   Zhisheng Xiao, et al.
0

Unsupervised outlier detection, which predicts if a test sample is an outlier or not using only the information from unlabelled inlier data, is an important but challenging task. Recently, methods based on the two-stage framework achieve state-of-the-art performance on this task. The framework leverages self-supervised representation learning algorithms to train a feature extractor on inlier data, and applies a simple outlier detector in the feature space. In this paper, we explore the possibility of avoiding the high cost of training a distinct representation for each outlier detection task, and instead using a single pre-trained network as the universal feature extractor regardless of the source of in-domain data. In particular, we replace the task-specific feature extractor by one network pre-trained on ImageNet with a self-supervised loss. In experiments, we demonstrate competitive or better performance on a variety of outlier detection benchmarks compared with previous two-stage methods, suggesting that learning representations from in-domain data may be unnecessary for outlier detection.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/01/2019

XGBOD: Improving Supervised Outlier Detection with Unsupervised Representation Learning

A new semi-supervised ensemble algorithm called XGBOD (Extreme Gradient ...
research
08/30/2022

SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation

The traditional homography estimation pipeline consists of four main ste...
research
03/22/2021

SSD: A Unified Framework for Self-Supervised Outlier Detection

We ask the following question: what training information is required to ...
research
06/13/2018

Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection

Learning expressive low-dimensional representations of ultrahigh-dimensi...
research
06/02/2019

Deep Unknown Intent Detection with Margin Loss

Identifying the unknown (novel) user intents that have never appeared in...
research
04/20/2021

Perceptual Loss for Robust Unsupervised Homography Estimation

Homography estimation is often an indispensable step in many computer vi...
research
09/16/2022

Self-Optimizing Feature Transformation

Feature transformation aims to extract a good representation (feature) s...

Please sign up or login with your details

Forgot password? Click here to reset