SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects

The unsupervised visual inspection of defects in industrial products poses a significant challenge due to substantial variations in product surfaces. Current unsupervised models struggle to strike a balance between detecting texture and object defects, lacking the capacity to discern latent representations and intricate features. In this paper, we present a novel self-supervised learning algorithm designed to derive an optimal encoder by tackling the renowned jigsaw puzzle. Our approach involves dividing the target image into nine patches, tasking the encoder with predicting the relative position relationships between any two patches to extract rich semantics. Subsequently, we introduce an affinity-augmentation method to accentuate differences between normal and abnormal latent representations. Leveraging the classic support vector data description algorithm yields final detection results. Experimental outcomes demonstrate that our proposed method achieves outstanding detection and segmentation performance on the widely used MVTec AD dataset, with rates of 95.8% and 96.8%, respectively, establishing a state-of-the-art benchmark for both texture and object defects. Comprehensive experimentation underscores the effectiveness of our approach in diverse industrial applications.

Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow

In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection. Based on only normal knowledge, visual anomaly detection has wide applications in industrial scenarios and has attracted significant attention. However, most existing methods fail to meet the requirements. In contrast, the proposed DTDF presents a new paradigm: it firstly leverages a pre-trained network to acquire multi-scale prior embeddings, followed by the development of a vision Transformer with dual attention mechanisms, namely self-attention and memorial-attention, to achieve two-level reconstruction for prior embeddings with the sequential and normality association. Additionally, we propose using normalizing flow to establish discriminative likelihood for the joint distribution of prior and reconstructions at each scale. The DADF achieves 98.3/98.4 of image/pixel AUROC on Mvtec AD; 83.7 of image AUROC and 67.4 of pixel sPRO on Mvtec LOCO AD benchmarks, demonstrating the effectiveness of our proposed approach.

Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection

This paper presents a novel framework, named Global-Local Correspondence Framework (GLCF), for visual anomaly detection with logical constraints. Visual anomaly detection has become an active research area in various real-world applications, such as industrial anomaly detection and medical disease diagnosis. However, most existing methods focus on identifying local structural degeneration anomalies and often fail to detect high-level functional anomalies that involve logical constraints. To address this issue, we propose a two-branch approach that consists of a local branch for detecting structural anomalies and a global branch for detecting logical anomalies. To facilitate local-global feature correspondence, we introduce a novel semantic bottleneck enabled by the visual Transformer. Moreover, we develop feature estimation networks for each branch separately to detect anomalies. Our proposed framework is validated using various benchmarks, including industrial datasets, Mvtec AD, Mvtec Loco AD, and the Retinal-OCT medical dataset. Experimental results show that our method outperforms existing methods, particularly in detecting logical anomalies.

Generalizable Industrial Visual Anomaly Detection with Self-Induction Vision Transformer

Industrial vision anomaly detection plays a critical role in the advanced intelligent manufacturing process, while some limitations still need to be addressed under such a context. First, existing reconstruction-based methods struggle with the identity mapping of trivial shortcuts where the reconstruction error gap is legible between the normal and abnormal samples, leading to inferior detection capabilities. Then, the previous studies mainly concentrated on the convolutional neural network (CNN) models that capture the local semantics of objects and neglect the global context, also resulting in inferior performance. Moreover, existing studies follow the individual learning fashion where the detection models are only capable of one category of the product while the generalizable detection for multiple categories has not been explored. To tackle the above limitations, we proposed a self-induction vision Transformer(SIVT) for unsupervised generalizable multi-category industrial visual anomaly detection and localization. The proposed SIVT first extracts discriminatory features from pre-trained CNN as property descriptors. Then, the self-induction vision Transformer is proposed to reconstruct the extracted features in a self-supervisory fashion, where the auxiliary induction tokens are additionally introduced to induct the semantics of the original signal. Finally, the abnormal properties can be detected using the semantic feature residual difference. We experimented with the SIVT on existing Mvtec AD benchmarks, the results reveal that the proposed method can advance state-of-the-art detection performance with an improvement of 2.8-6.3 in AUROC, and 3.3-7.6 in AP.

Reference-Based Autoencoder for Surface Defect Detection

Due to the extreme imbalance in the number of normal data and abnormal data, visual anomaly detection is important for the development of industrial automatic product quality inspection. Unsupervised methods based on reconstruction and embedding have been widely studied for anomaly detection, of which reconstruction-based methods are the most popular. However, establishing a unified model for textured surface defect detection remains a challenge because these surfaces can vary in homogeneous and non regularly ways. Furthermore, existing reconstruction-based methods do not have a strong ability to convert the defect feature to the normal feature. To address these challenges, we propose a novel unsupervised reference-based autoencoder (RB-AE) to accurately inspect a variety of textured defects. Unlike most reconstruction-based methods, artificial defects and a novel pixel-level discrimination loss function are utilized for training to enable the model to obtain pixel-level discrimination ability. First, the RB-AE employs an encoding module to extract multi-scale features of the textured surface. Subsequently, a novel reference-based attention module (RBAM) is proposed to convert the defect features to normal features to suppress the reconstruction of defects. In addition, RBAM can also effectively suppress the defective feature residual caused by skip-connection. Next, a decoding module utilizes the repaired features to reconstruct the normal texture background. Finally, a novel multiscale feature discrimination module (MSFDM) is employed to defect detection and segmentation.

Siamese Transition Masked Autoencoders as Uniform Unsupervised Visual Anomaly Detector

Unsupervised visual anomaly detection conveys practical significance in many scenarios and is a challenging task due to the unbounded definition of anomalies. Moreover, most previous methods are application-specific, and establishing a unified model for anomalies across application scenarios remains unsolved. This paper proposes a novel hybrid framework termed Siamese Transition Masked Autoencoders(ST-MAE) to handle various visual anomaly detection tasks uniformly via deep feature transition. Concretely, the proposed method first extracts hierarchical semantics features from a pre-trained deep convolutional neural network and then develops a feature decoupling strategy to split the deep features into two disjoint feature patch subsets. Leveraging the decoupled features, the ST-MAE is developed with the Siamese encoders that operate on each subset of feature patches and perform the latent representations transition of two subsets, along with a lightweight decoder that reconstructs the original feature from the transitioned latent representation. Finally, the anomalous attributes can be detected using the semantic deep feature residual. Our deep feature transition scheme yields a nontrivial and semantic self-supervisory task to extract prototypical normal patterns, which allows for learning uniform models that generalize well for different visual anomaly detection tasks. The extensive experiments conducted demonstrate that the proposed ST-MAE method can advance state-of-the-art performance on multiple benchmarks across application scenarios with a superior inference efficiency, which exhibits great potential to be the uniform model for unsupervised visual anomaly detection.

A Feature Memory Rearrangement Network for Visual Inspection of Textured Surface Defects Toward Edge Intelligent Manufacturing

Recent advances in the industrial inspection of textured surfaces-in the form of visual inspection-have made such inspections possible for efficient, flexible manufacturing systems. We propose an unsupervised feature memory rearrangement network (FMR-Net) to accurately detect various textural defects simultaneously. Consistent with mainstream methods, we adopt the idea of background reconstruction; however, we innovatively utilize artificial synthetic defects to enable the model to recognize anomalies, while traditional wisdom relies only on defect-free samples. First, we employ an encoding module to obtain multiscale features of the textured surface. Subsequently, a contrastive-learning-based memory feature module (CMFM) is proposed to obtain discriminative representations and construct a normal feature memory bank in the latent space, which can be employed as a substitute for defects and fast anomaly scores at the patch level. Next, a novel global feature rearrangement module (GFRM) is proposed to further suppress the reconstruction of residual defects. Finally, a decoding module utilizes the restored features to reconstruct the normal texture background. In addition, to improve inspection performance, a two-phase training strategy is utilized for accurate defect restoration refinement, and we exploit a multimodal inspection method to achieve noise-robust defect localization. We verify our method through extensive experiments and test its practical deployment in collaborative edge--cloud intelligent manufacturing scenarios by means of a multilevel detection method, demonstrating that FMR-Net exhibits state-of-the-art inspection accuracy and shows great potential for use in edge-computing-enabled smart industries.