# LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space

arXiv: https://arxiv.org/abs/2410.10234 · HTML: https://mlsanity.com/paper/2410.10234/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [Sub-Image Anomaly Detection with Deep Pyramid Correspondences](https://mlsanity.com/paper/2005.02357/) (2020)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows](https://mlsanity.com/paper/2111.07677/) (2021)
- [EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies](https://mlsanity.com/paper/2303.14535/) (2023)
- [Deep Industrial Image Anomaly Detection: A Survey](https://mlsanity.com/paper/2301.11514/) (2023)
- [Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders](https://mlsanity.com/paper/2210.12316/) (2022)
- [BMAD: Benchmarks for Medical Anomaly Detection](https://mlsanity.com/paper/2306.11876/) (2023)
- [A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization](https://mlsanity.com/paper/2407.09359/) (2024)
- [Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2310.14228/) (2023)
- [Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization](https://mlsanity.com/paper/2305.11718/) (2023)
- [Self-Supervised Masking for Unsupervised Anomaly Detection and Localization](https://mlsanity.com/paper/2205.06568/) (2022)
- [MAEDAY: MAE for few and zero shot AnomalY-Detection](https://mlsanity.com/paper/2211.14307/) (2022)
- [Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation](https://mlsanity.com/paper/2305.13607/) (2023)
- [Component-aware anomaly detection framework for adjustable and logical industrial visual inspection](https://mlsanity.com/paper/2305.08509/) (2023)
- [Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection](https://mlsanity.com/paper/2303.05768/) (2023)
- [Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection](https://mlsanity.com/paper/2312.13783/) (2023)
- [Are we certain it's anomalous?](https://mlsanity.com/paper/2211.09224/) (2022)

## Abstract (arXiv)

Detecting anomalies such as an incorrect combination of objects or deviations in their positions is a challenging problem in unsupervised anomaly detection (AD). Since conventional AD methods mainly focus on local patterns of normal images, they struggle with detecting logical anomalies that appear in the global patterns. To effectively detect these challenging logical anomalies, we introduce Logical Anomaly Detection with Masked Image Modeling (LADMIM), a novel unsupervised AD framework that harnesses the power of masked image modeling and discrete representation learning. Our core insight is that predicting the missing region forces the model to learn the long-range dependencies between patches. Specifically, we formulate AD as a mask completion task, which predicts the distribution of discrete latents in the masked region. As a distribution of discrete latents is invariant to the low-level variance in the pixel space, the model can desirably focus on the logical dependencies in the image, which improves accuracy in the logical AD. We evaluate the AD performance on five benchmarks and show that our approach achieves compatible performance without any pre-trained segmentation models. We also conduct comprehensive experiments to reveal the key factors that influence logical AD performance.