Pith. sign in

REVIEW 8 cited by

Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.02011 v3 pith:EJ76PK7H submitted 2018-07-05 cs.CV cs.LG

Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders

Paul Bergmann , Sindy L\"owe , Michael Fauser , David Sattlegger , Carsten Steger This is my paper
classification cs.CV cs.LG
keywords autoencodersdefectreconstructionsegmentationstructuralunsupervisedapproachesdataset
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Convolutional autoencoders have emerged as popular methods for unsupervised defect segmentation on image data. Most commonly, this task is performed by thresholding a pixel-wise reconstruction error based on an $\ell^p$ distance. This procedure, however, leads to large residuals whenever the reconstruction encompasses slight localization inaccuracies around edges. It also fails to reveal defective regions that have been visually altered when intensity values stay roughly consistent. We show that these problems prevent these approaches from being applied to complex real-world scenarios and that it cannot be easily avoided by employing more elaborate architectures such as variational or feature matching autoencoders. We propose to use a perceptual loss function based on structural similarity which examines inter-dependencies between local image regions, taking into account luminance, contrast and structural information, instead of simply comparing single pixel values. It achieves significant performance gains on a challenging real-world dataset of nanofibrous materials and a novel dataset of two woven fabrics over the state of the art approaches for unsupervised defect segmentation that use pixel-wise reconstruction error metrics.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision

    cs.CV 2026-06 unverdicted novelty 7.0

    Introduces TGAD benchmark showing superficial text conditioning in multimodal anomaly detection across prompt-sensitivity, component-tagged, and realistic APD scenarios.

  2. Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    Real-IAD-MVN supplies multi-view normal vector data and a reconstruction baseline that outperforms prior multimodal methods for geometric industrial anomaly detection.

  3. SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling

    cs.CV 2026-02 accept novelty 7.0

    A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.

  4. AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

    cs.CV 2026-01 conditional novelty 7.0

    AnomalyVFM converts vision foundation models into zero-shot anomaly detectors via three-stage synthetic dataset generation plus low-rank adapters and weighted pixel loss, reaching 94.1% average image AUROC across nine...

  5. Text-Guided Multimodal Unified Industrial Anomaly Detection

    cs.CV 2026-04 unverdicted novelty 6.0

    A text-semantics-guided multimodal framework with geometry-aware mapping and object-conditioned text adaptation achieves state-of-the-art unsupervised anomaly detection and localization on RGB-3D industrial datasets w...

  6. Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization

    cs.CV 2023-09 unverdicted novelty 6.0

    A new framework learns low-dimensional subspaces from nominal samples and reconstructs target deep embeddings via self-expressive linear combinations to localize anomalies, claiming SOTA on three benchmarks.

  7. AUCp: Pseudo-AUC for Inference Model Selection with Unlabeled Validation Data in Abnormality Detection

    cs.CV 2026-06 unverdicted novelty 5.0

    AUCp selects inference models for unsupervised abnormality detection by computing AUC after labeling all test samples as positive, shown to outperform conventional metrics when normal training data is representative.

  8. MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection

    cs.CV 2026-06 unverdicted novelty 4.0

    MambaADv2 evolves Mamba state space models with hybrid blocks, frequency convolutions, and adaptive scanning for improved unsupervised anomaly detection.