mlsanityData to 14 Oct 2026

DART: A Vision-Language Foundation Model for Comprehensive Rope Condition Monitoring

arXiv 2605.04943 ↗First posted 6 May 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The condition monitoring (CM) of synthetic fibre ropes (SFRs) used in offshore, maritime, and industrial settings demands more than a classifier: inspectors need continuous severity estimates, maintenance recommendations, anomaly flags, deterioration timelines, and automated reports, all from a single inspection image. We present DART (Damage Assessment via Rope Transformer), a vision-language foundation model that addresses the full rope inspection workflow through a unified multi-task architecture. DART extends the Joint-Embedding Predictive Architecture (JEPA) to the cross-modal domain by coupling a Vision Transformer (ViT-H/14) with Llama-3.2-3B-Instruct via a Severity-Conditioned Cross-Modal Fusion (SC-CMF) module. Three architectural innovations drive the model's versatility: (1) HD-MASK, a saliency-guided masking strategy that focuses self-supervised reconstruction on damage-dense patches; (2) per-class learnable severity gates that adaptively weight language grounding by damage category; and (3) a Contrastive Damage Disentanglement (CDD) loss that shapes the embedding space to simultaneously encode damage type, severity ordering, and cross-modal semantics. Trained once on 4,270 images spanning 14 fine-grained rope damage classes, the frozen DART backbone supports downstream tasks without any task-specific fine-tuning: damage classification (93.22 % accuracy, 91.04 % macro-F1, +38.5 pp over a vision-only baseline), continuous severity regression (Spearman rho = 0.94, within-1-ordinal accuracy 99.6 %), few-shot recognition (89.2 % macro-F1 at 20 shots). These results demonstrate that DART functions as a general-purpose CM backbone that goes well beyond classification, providing actionable inspection intelligence from a single shared representation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

28 of 50 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  11. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  12. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
16 more
  1. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  2. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  3. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  5. 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecturecited by 1,039
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  7. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  8. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  9. 2024Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learningcited by 20
  10. 2026VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Modelscited by 17
  11. 2018Detection and Segmentation of Manufacturing Defects with Convolutional Neural Networks and Transfer Learningcited by 16
  12. 2024COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detectioncited by 13
  13. 2024M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecturecited by 13
  14. 2023Defect Detection in Synthetic Fibre Ropes using Detectron2 Frameworkcited by 3
  15. 2023Imagery Dataset for Condition Monitoring of Synthetic Fibre Ropescited by 2
  16. 2026Imagery Dataset for Remaining Useful Life Estimation of Synthetic Fibre Ropescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Seeing the Unseen: Towards Training-Free Inspection for Wind Turbine Blades Using Knowledge-Augmented Vision Language Models
  2. 2026A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection
  3. 2026Fine-Tuning Vision-Language Models for Understanding Current Damage and Scoring Priority with Quality Guard Agent
  4. 2026Quantized Vision-Language Models for Damage Assessment: A Comparative Study of LLaVA-1.5-7B Quantization Levels
  5. 2026Synthetic Defect Image Generation for Power Line Insulator Inspection Using Multimodal Large Language Models
  6. 2025Language-in-the-Loop Culvert Inspection on the Erie Canal
  7. 2025InspectVLM: Unified in Theory, Unreliable in Practice
  8. 2025LVLMs as inspectors: an agentic framework for category-level structural defect annotation