SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Track

• URL: http://arxiv.org/abs/2605.14808v1
• Date: Thu, 14 May 2026 13:22:02 GMT
• Title: SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Track
• Abstract summary: We propose a training-free and class-agnostic anomaly detection pipeline based on the work of SuperAD.<n>Our approach improves generalization through several modifications designed to enhance robustness under distribution shifts.<n>We achieve segmentation F1 scores of $62.61%$, $57.42%$, and $54.35%$ on test public, private, and private mixed of MVTec AD 2 respectively.
• Score: 13.401733929149877
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual anomaly detection (AD) for industrial inspection is a highly relevant task in modern production environments. The problem becomes particularly challenging when training and deployment data differ due to changes in acquisition conditions during production. In the VAND 4.0 Industrial Track, models must remain robust under distribution shifts such as varying illumination and their performance is assessed on the MVTec AD 2 dataset. To address this setting, we propose a training-free and class-agnostic anomaly detection pipeline based on the work of SuperAD. Our approach improves generalization through several modifications designed to enhance robustness under distribution shifts. These adaptations include using a DINOv3 backbone, overlapping patch-wise processing, intensity-based augmentations, improved memory-bank subsampling for better coverage of the data distribution, and iterative morphological closing for cleaner and more spatially consistent anomaly maps. Unlike methods that rely on class-specific architectures or per-class hyperparameter tuning, our method uses a single architecture and one shared hyperparameter configuration across all object classes. This makes the approach well suited for industrial deployment, where product variants and appearance changes must be handled with minimal adaptation effort. We achieve segmentation F1 scores of $62.61\%$, $57.42\%$, and $54.35\%$ on test public, private, and private mixed of MVTec AD 2 respectively, thereby outperforming SuperAD and other state-of-the-art methods. Code is available at https://github.com/LukasRoom/SuperADD.

Related papers

• Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts [24.352848169805426]
  We propose an analogy-based method that adapts VLA models under environmental shifts through weight vector arithmetic.<n>Unlike prior approaches, DART requires collecting only a single demonstration, enabling efficient adaptation.<n>In both simulated and real-world experiments, DART outperforms existing VLA adaptation methods in one-shot scenarios.
  arXiv  Detail & Related papers  (2026-07-01T09:13:40Z)
• Deep Reprogramming Distillation for Medical Foundation Models [74.76894329393512]
  We propose a novel framework called Deep Reprogramming Distillation (DRD) to combat the general adaptation challenge.<n>Specifically, DRD introduces the novel reprogramming module that on the one side overcomes the domain and task discrepancy between pretraining and downstream scenarios.<n>To mitigate variability under different training conditions, we design a centered kernel alignment (CKA) distillation method to promote robust knowledge transfer.
  arXiv  Detail & Related papers  (2026-05-06T03:22:39Z)
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale [92.09717763663873]
  We present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design.<n>At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy.<n>We show that MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods.
  arXiv  Detail & Related papers  (2026-04-06T15:44:18Z)
• The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation [86.83038620308423]
  Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data.<n>We propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP.
  arXiv  Detail & Related papers  (2026-03-23T12:48:38Z)
• Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations [0.0]
  Unsupervised change detection (UCD) in remote sensing aims to localise semantic changes between two images of the same region without relying on labelled data during training.<n>We propose MaSoN, an end-to-end UCD framework that synthesises diverse changes directly in the latent feature space during training.<n>It generates changes that are dynamically estimated using feature statistics of target data, enabling diverse yet data-driven variation aligned with the target domain.
  arXiv  Detail & Related papers  (2026-02-23T14:27:36Z)
• Universal Transformation of One-Class Classifiers for Unsupervised Anomaly Detection [51.73001988341294]
  Anomaly detection is typically formulated as a one-class classification problem.<n>We present a dataset folding method that transforms an arbitrary one-class classifier-based anomaly detector into a fully unsupervised method.
  arXiv  Detail & Related papers  (2026-02-13T16:54:12Z)
• Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student Networks [11.543429175824905]
  Anomaly detection plays an important role in various real-world applications.<n>Recent methods have attempted to address general anomaly detection, but their performance remains sensitive to dataset-specific settings and single-class tasks.<n>We propose a novel dual-model ensemble approach based on knowledge distillation (KD) to bridge this gap.
  arXiv  Detail & Related papers  (2025-09-29T08:31:31Z)
• Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence [131.41894248194995]
  We propose context-oriented decomposition adaptation (CorDA), a novel method that initializes adapters in a task-aware manner.<n>Thanks to the task awareness, our method enables two optional adaptation modes, knowledge-preserved mode (KPM) and instruction-previewed mode (IPM)
  arXiv  Detail & Related papers  (2025-06-16T07:55:14Z)
• 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)
• Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS) [3.4519649635864584]
  This work introduces the Domain Adaptation Neural Network with Cyclic Supervision (DBACS) approach. DBACS addresses the issue of model generalization through domain adaptation, specifically for heterogeneous data. This work also includes subspace alignment and a multi-view learning that deals with heterogeneous representations.
  arXiv  Detail & Related papers  (2023-01-03T10:56:25Z)
• Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation [120.69747175899421]
  Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. We propose a computationally-efficient dual form of the robust OT optimization that is amenable to modern deep learning applications. Our approach can train state-of-the-art GAN models on noisy datasets corrupted with outlier distributions.
  arXiv  Detail & Related papers  (2020-10-12T17:13:40Z)

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.