RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images

• URL: http://arxiv.org/abs/2505.21152v1
• Date: Tue, 27 May 2025 13:04:48 GMT
• Title: RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images
• Abstract summary: Unsupervised anomaly detection in real-world scenarios is an important task.<n>Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark.<n>We propose a robust framework RoBiS, which consists of three core modules.
• Score: 3.226330965024265
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust unsupervised anomaly detection (AD) in real-world scenarios is an important task. Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark due to its complex real-world challenges. To solve this problem, we propose a robust framework RoBiS, which consists of three core modules: (1) Swin-Cropping, a high-resolution image pre-processing strategy to preserve the information of small anomalies through overlapping window cropping. (2) The data augmentation of noise addition and lighting simulation is carried out on the training data to improve the robustness of AD model. We use INP-Former as our baseline, which could generate better results on the various sub-images. (3) The traditional statistical-based binarization strategy (mean+3std) is combined with our previous work, MEBin (published in CVPR2025), for joint adaptive binarization. Then, SAM is further employed to refine the segmentation results. Compared with some methods reported by the MVTec AD 2, our RoBiS achieves a 29.2% SegF1 improvement (from 21.8% to 51.00%) on Test_private and 29.82% SegF1 gains (from 16.7% to 46.52%) on Test_private_mixed. Code is available at https://github.com/xrli-U/RoBiS.

Related papers

• D3S2: Diffusion-Guided Dataset Distillation for Semantic Segmentation [8.30626759264565]
  We identify three key challenges for segmentation DD: (i) long-tailed class imbalance, (ii) the need for strict pixel-wise alignment between images and dense labels, and (iii) the high computational cost of optimizing high-resolution data with complex models.<n>In Class-Balanced Mask Selection, we construct a representative mask set via a greedy strategy that prioritizes underrepresented classes.<n>In Diffusion-Guided Image Synthesis, we employ a pretrained layout-to-image diffusion model to generate images conditioned on the selected masks, naturally ensuring alignment.
  arXiv  Detail & Related papers  (2026-05-24T12:01:38Z)
• Boundary-Aware Test-Time Adaptation for Zero-Shot Medical Image Segmentation [12.159529070716824]
  BA-TTA-SAM is a test-time adaptation framework that enhances the zero-shot segmentation performance of SAM via test-time adaptation.<n>Our framework consistently outperforms state-of-the-art models in medical image segmentation.
  arXiv  Detail & Related papers  (2025-12-04T07:08:21Z)
• PRISM: Distributed Inference for Foundation Models at Edge [73.54372283220444]
  PRISM is a communication-efficient and compute-aware strategy for distributed Transformer inference on edge devices.<n>We evaluate PRISM on ViT, BERT, and GPT-2 across diverse datasets.
  arXiv  Detail & Related papers  (2025-07-16T11:25:03Z)
• SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect [17.160007050126403]
  We propose a fully training-free anomaly detection and segmentation method based on feature extraction using the DINOv2 model named SuperAD.<n>Our method achieves competitive results on both test sets of the MVTec AD 2 dataset.
  arXiv  Detail & Related papers  (2025-05-26T09:29:27Z)
• Evaluating and Enhancing Segmentation Model Robustness with Metamorphic Testing [10.564949684320727]
  SegRMT is a testing approach that leverages genetic algorithms to optimize sequences of spatial and spectral transformations.<n>Our experiments show that SegRMT reduces DeepLabV3's mean Intersection over Union (mIoU) to 6.4%.<n>When used for adversarial training, SegRMT boosts model performance, achieving mIoU improvements up to 73%.
  arXiv  Detail & Related papers  (2025-04-03T07:15:45Z)
• Foundation Models for Structural Health Monitoring [17.37816294594306]
  We propose for the first time the use of Transformer neural networks, with a Masked Auto-Encoder architecture, as Foundation Models for Structural Health Monitoring. We demonstrate the ability of these models to learn generalizable representations from multiple large datasets through self-supervised pre-training. We showcase the effectiveness of our foundation models using data from three operational viaducts.
  arXiv  Detail & Related papers  (2024-04-03T13:32:44Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation [61.027468209465354]
  We introduce a novel learning scheme named weakly semi-supervised instance segmentation (WSSIS) with point labels. We propose a method for WSSIS that can effectively leverage the budget-friendly point labels as a powerful weak supervision source. We conduct extensive experiments on COCO and BDD100K datasets, and the proposed method achieves promising results comparable to those of the fully-supervised model.
  arXiv  Detail & Related papers  (2023-03-27T10:11:22Z)
• Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval [51.42470171051007]
  This paper tackles the Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning. By combining two fundamental learning approaches in DML, e.g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR. We show that Modality-Aware Triplet Hard Mining (MATHM) enhances the baseline with three types of pairwise learning.
  arXiv  Detail & Related papers  (2021-12-15T08:36:44Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Boosting Randomized Smoothing with Variance Reduced Classifiers [4.110108749051657]
  We motivate why ensembles are a particularly suitable choice as base models for Randomized Smoothing (RS) We empirically confirm this choice, obtaining state of the art results in multiple settings.
  arXiv  Detail & Related papers  (2021-06-13T08:40:27Z)
• ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning [91.13797346047984]
  We introduce ADAHESSIAN, a second order optimization algorithm which dynamically incorporates the curvature of the loss function via ADAptive estimates. We show that ADAHESSIAN achieves new state-of-the-art results by a large margin as compared to other adaptive optimization methods.
  arXiv  Detail & Related papers  (2020-06-01T05:00:51Z)

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.