Back to search

Georgia Institute of Technology

Robust Learning for Fine-Grained Anomaly Detection in a Data-Rich but Label-Rare Environment

Abstract

dc:description.abstract

Image-based anomaly detection is of vital importance across various industrial, environmental, and medical domains. The continuous evolution of sensor technologies has facilitated the collection and storage of high-resolution, multichannel, and multi-view measurement signals, providing detailed product insights. However, annotating defects remains challenging due to the costly labeling process and the infrequent occurrence of defects in modern manufacturing processes, leading to a scarcity of labeled data and a label-rare environment. Moreover, contemporary high-value and safety-critical applications necessitate fine-grained anomaly detection capabilities. Yet, achieving such precision in anomaly detection, in the absence of adequate anomaly supervision signals, presents a huge challenge for modern algorithms. To address these challenges, this doctoral thesis delves into robust learning algorithms designed to achieve robust signal restoration under unknown gross corruptions. In the context of anomaly detection, anomalies often manifest as sparse corruptions within an otherwise clean background signal. This thesis endeavors to extend the capabilities of robust learning algorithms to tackle various real-world challenges. Specifically, three important topics are investigated in this thesis: (1) Additive Tensor Decomposition (ATD): Tensor data is becoming increasingly popular for storing high-resolution, multichannel, and multi-view measurement signals. To accommodate these new data types within a data-rich environment, traditional robust learning algorithms are being generalized to handle tensor data. As part of this effort, an Additive Tensor Decomposition (ATD) framework has been proposed. Within this ATD framework, a set of tensor structural priors are defined to effectively model clean background signals, offering a flexible means of integrating engineering knowledge. The framework formulates a high-dimensional optimization problem, incorporating regularization terms based on these tensor structural priors, to decompose the input tensor into multiple components representing different structural information such as normal background and anomalies. Simulation examples and a real case study in medical image analysis are conducted to demonstrate the versatility and effectiveness of the ATD framework. (2) Compressed Smooth Sparse Decomposition (CSSD): An immediate challenge stemming from advancements in measurement technology is the handling of storage, transmission, and computation burdens associated with measurement signals. For instance, achieving real-time high-precision inspection of surface defects often requires the high-speed transmission and processing of large volumes of high-resolution images. This considerable amount of high-resolution image data presents significant challenges not only for the speed of decomposition-based image processing algorithms but also for the storage and transmission of the data itself. To address this challenge, a fast and data-efficient method is developed for sparse anomaly detection in high-resolution images with a smooth background. This method, termed Compressed Smooth Sparse Decomposition (CSSD), is a one-step approach that integrates compressive image acquisition with decomposition-based image processing techniques. Theoretical properties regarding the feasibility of applying CSSD are thoroughly examined. Furthermore, the proposed framework is generalized to a tensor signal setting. Simulation examples and case studies across various applications demonstrate the effectiveness of the proposed framework. (3) Distributional-assumption-free robust learning: In scenarios involving complex signals like computed tomography (CT) scans of human organs or inspection images of manufacturing products with diverse surface patterns, simplistic statistical priors often prove insufficient. Current robust learning methods, which rely on those statistical priors such as low rank and smoothness to reconstruct normal signals and identify abnormal components, frequently fall short in such applications. The abundance of large-scale normal data in high-yield advanced manufacturing applications motivates the incorporation of learned priors into the robust learning framework, thereby modeling signals in a distributional-assumption-free manner. In this thesis, a set of distributional-assumption-free robust learning methods are developed and presented in two consecutive chapters: Part I: Patch Autoencoder Based Deep Image Decomposition (PAEDID) in Chapter 4, and Part II: Robust GAN inversion (RGI) methods in Chapter 5. In these chapters, clean background signals are modeled as deep priors learned from large datasets of clean images, encompassing normal product variations. Meanwhile, anomalies are modeled as sparse corruptions to these clean signals. The proposed methods represent significant generalizations of traditional robust machine learning methods into the deep learning era. They seamlessly integrate robustness from a robust learning framework with the modeling capabilities of deep neural network learned priors, enabling the resolution of application problems that were previously challenging for either unsupervised deep learning or statistical robust learning methods in isolation.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Industrial and Systems Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Mou, Shancong
Advisor dc:contributor.advisor
  • Shi, Jianjun
Committee members dc:contributor.committeemember
  • Li, Jing
  • Mei, Yajun
  • Paynabar, Kamran
  • Yan, Hao

Subjects

dc:subject × 2

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/77754

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Mou, Shancong. Robust Learning for Fine-Grained Anomaly Detection in a Data-Rich but Label-Rare Environment. Doctoral thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/77754