Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection

• URL: http://arxiv.org/abs/2312.13783v2
• Date: Mon, 15 Apr 2024 07:18:45 GMT
• Title: Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection
• Authors: Soopil Kim, Sion An, Philip Chikontwe, Myeongkyun Kang, Ehsan Adeli, Kilian M. Pohl, Sang Hyun Park,
• Abstract summary: We introduce a novel component segmentation model for Logical anomalies (LA) detection. To ensure consistent segmentation across unlabeled images, we employ a histogram matching loss in conjunction with an entropy loss. For effective LA detection, we propose an adaptive scaling strategy to standardize anomaly scores from different memory banks in inference.
• Score: 11.996050578189056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types through segmentation. However, curation of pixel-level annotations for semantic segmentation is both time-consuming and expensive. Although there are some prior few-shot or unsupervised co-part segmentation algorithms, they often fail on images with industrial object. These images have components with similar textures and shapes, and a precise differentiation proves challenging. In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints. To ensure consistent segmentation across unlabeled images, we employ a histogram matching loss in conjunction with an entropy loss. As segmentation predictions play a crucial role, we propose to enhance both local and global sample validity detection by capturing key aspects from visual semantics via three memory banks: class histograms, component composition embeddings and patch-level representations. For effective LA detection, we propose an adaptive scaling strategy to standardize anomaly scores from different memory banks in inference. Extensive experiments on the public benchmark MVTec LOCO AD reveal our method achieves 98.1% AUROC in LA detection vs. 89.6% from competing methods.

Related papers

• Counterfactuals and Uncertainty-Based Explainable Paradigm for the Automated Detection and Segmentation of Renal Cysts in Computed Tomography Images: A Multi-Center Study [1.83277723272657]
  Routine computed tomography (CT) scans often detect a wide range of renal cysts, some of which may be malignant. Current segmentation methods, however, do not offer sufficient interpretability at the feature and pixel levels. We developed an interpretable segmentation framework and validated it on a multi-centric dataset.
  arXiv  Detail & Related papers  (2024-08-07T14:14:05Z)
• Visual Context-Aware Person Fall Detection [52.49277799455569]
  We present a segmentation pipeline to semi-automatically separate individuals and objects in images. Background objects such as beds, chairs, or wheelchairs can challenge fall detection systems, leading to false positive alarms. We demonstrate that object-specific contextual transformations during training effectively mitigate this challenge.
  arXiv  Detail & Related papers  (2024-04-11T19:06:36Z)
• PDiscoNet: Semantically consistent part discovery for fine-grained recognition [62.12602920807109]
  We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods.
  arXiv  Detail & Related papers  (2023-09-06T17:19:29Z)
• Self-Supervised Correction Learning for Semi-Supervised Biomedical Image Segmentation [84.58210297703714]
  We propose a self-supervised correction learning paradigm for semi-supervised biomedical image segmentation. We design a dual-task network, including a shared encoder and two independent decoders for segmentation and lesion region inpainting. Experiments on three medical image segmentation datasets for different tasks demonstrate the outstanding performance of our method.
  arXiv  Detail & Related papers  (2023-01-12T08:19:46Z)
• Learning to Annotate Part Segmentation with Gradient Matching [58.100715754135685]
  This paper focuses on tackling semi-supervised part segmentation tasks by generating high-quality images with a pre-trained GAN. In particular, we formulate the annotator learning as a learning-to-learn problem. We show that our method can learn annotators from a broad range of labelled images including real images, generated images, and even analytically rendered images.
  arXiv  Detail & Related papers  (2022-11-06T01:29:22Z)
• Contrastive Image Synthesis and Self-supervised Feature Adaptation for Cross-Modality Biomedical Image Segmentation [8.772764547425291]
  CISFA builds on image domain translation and unsupervised feature adaptation for cross-modality biomedical image segmentation. We use a one-sided generative model and add a weighted patch-wise contrastive loss between sampled patches of the input image and the corresponding synthetic image. We evaluate our methods on segmentation tasks containing CT and MRI images for abdominal cavities and whole hearts.
  arXiv  Detail & Related papers  (2022-07-27T01:49:26Z)
• Mixed-UNet: Refined Class Activation Mapping for Weakly-Supervised Semantic Segmentation with Multi-scale Inference [28.409679398886304]
  We develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets.
  arXiv  Detail & Related papers  (2022-05-06T08:37:02Z)
• Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation [72.33139350241044]
  Weakly Supervised Semantic COCO (WSSS) based on image-level labels has attracted much attention due to low annotation costs. We propose a Self-supervised Image-specific Prototype Exploration (SIPE) that consists of an Image-specific Prototype Exploration (IPE) and a General-Specific Consistency (GSC) loss. Our SIPE achieves new state-of-the-art performance using only image-level labels.
  arXiv  Detail & Related papers  (2022-03-06T09:01:03Z)
• Unsupervised Part Discovery from Contrastive Reconstruction [90.88501867321573]
  The goal of self-supervised visual representation learning is to learn strong, transferable image representations. We propose an unsupervised approach to object part discovery and segmentation. Our method yields semantic parts consistent across fine-grained but visually distinct categories.
  arXiv  Detail & Related papers  (2021-11-11T17:59:42Z)
• A Weakly-Supervised Semantic Segmentation Approach based on the Centroid Loss: Application to Quality Control and Inspection [6.101839518775968]
  We propose and assess a new weakly-supervised semantic segmentation approach making use of a novel loss function. The performance of the approach is evaluated against datasets from two different industry-related case studies.
  arXiv  Detail & Related papers  (2020-10-26T09:08:21Z)
• Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation [4.626338154327536]
  In industrial inspection tasks, it is common to capture abundant defect-free image samples but very limited anomalous ones. This paper tackles the challenging few-shot defect segmentation task with sufficient normal (defect-free) training images but very few anomalous ones. We present two effective regularization techniques via incorporating abundant defect-free images into the training of a UNet-like encoder-decoder defect segmentation network.
  arXiv  Detail & Related papers  (2020-07-18T14:15:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.