IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation

• URL: http://arxiv.org/abs/2604.12440v1
• Date: Tue, 14 Apr 2026 08:29:31 GMT
• Title: IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation
• Abstract summary: Real-world industrial inspection requires localizing defects, explaining them in natural language and generating controlled defect edits.<n>We propose IAD-Unify, a dual-encoder unified framework in which a frozen DINOv2-based region expert supplies precise anomaly evidence.<n>IAD-Unify achieves strong performance on the MMAD benchmark, including categories unseen during training, demonstrating robust cross-category generalization.
• Score: 21.900464211494022
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world industrial inspection requires not only localizing defects, but also explaining them in natural language and generating controlled defect edits. However, existing approaches fail to jointly support all three capabilities within a unified framework and evaluation protocol. We propose IAD-Unify, a dual-encoder unified framework in which a frozen DINOv2-based region expert supplies precise anomaly evidence to a shared Qwen3.5-4B vision-language backbone via lightweight token injection, jointly enabling anomaly segmentation, region-grounded understanding, and mask-guided generation. To enable unified evaluation, we further construct Anomaly-56K, a comprehensive unified multi-task IAD evaluation platform, spanning 59,916 images across 24 categories and 104 defect variants. Controlled ablations yield four findings: (i) region grounding is the decisive mechanism for understanding, removing it degrades location accuracy by >76 pp; (ii) predicted-region performance closely matches oracle, confirming deployment viability; (iii) region-grounded generation achieves the best full-image fidelity and masked-region perceptual quality; and (iv) pre-initialized joint training improves understanding at negligible generation cost (-0.16 dB). IAD-Unify further achieves strong performance on the MMAD benchmark, including categories unseen during training, demonstrating robust cross-category generalization.

Related papers

• Continuity-Driven Representation Learning for Industrial Defect Detection [10.126273003671388]
  Industrial defect detection differs from natural-image object detection because inspection images contain large normal-dominant regions with repetitive structures.<n>We propose a continuity-driven representation regularization framework that exploits normal-dominant regions as dense auxiliary supervision.
  arXiv  Detail & Related papers  (2026-08-18T04:31:55Z)
• MS-MFAD : Multimodal large language models for Face Anti-spoofing Detection [25.077055201475442]
  We propose Multimodal Large Language Models (MFAD) for face anti-spoofing detection.<n>MFAD activates intrinsic reasoning capabilities of Multimodal Large Language Models via a fine-grained pixel-semantic anchoring mechanism.<n>By annotating only 1,000 precise masks per attack category, we generate reasoning evidence chains strictly corresponding to spoofed regions.
  arXiv  Detail & Related papers  (2026-08-18T03:38:59Z)
• ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling [62.983372215479925]
  Streaming and generative systems require incremental estimation from partial audio.<n>We propose ANCHOR, reformulating incremental assessment as a multi-resolution autore task.<n> Experiments show substantial robustness under partial input, including a 48% PLCMOS error reduction on 2-second prefixes.
  arXiv  Detail & Related papers  (2026-06-08T22:46:30Z)
• A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision [8.253092044813593]
  We introduce Text-Guided Anomaly Detection (TGAD), a structured benchmark that progressively increases the functional role of language across three scenarios.<n>We evaluate one representative model per paradigm: generative large vision-language, training-free discriminative, and embedding-adaptive discriminative.
  arXiv  Detail & Related papers  (2026-06-01T09:50:30Z)
• Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition [6.313563501854241]
  We propose a unified Prototype-driven Adrial Alignment (PAA) framework for cross-corpus EEG emotion recognition.<n>The proposed framework reformulates emotion recognition as a relation-driven representation learning problem.<n>Experiments on SEED, SEED-IV, and SEED-V demonstrate state-of-the-art performance under four cross-corpus evaluation protocols.
  arXiv  Detail & Related papers  (2026-03-18T02:28:05Z)
• AINet: Anchor Instances Learning for Regional Heterogeneity in Whole Slide Image [61.54860340942449]
  We introduce a novel concept of anchor instance (AI), a compact subset of instances that are representative within their regions (local) and discriminative at the bag (global) level.<n>These AIs act as semantic references to guide interactions across regions, correcting non-discriminative patterns while preserving regional diversity.<n>We develop a concise yet effective framework, AINet, which employs a simple predictor and surpasses state-of-the-art methods with substantially fewer FLOPs and parameters.
  arXiv  Detail & Related papers  (2026-02-21T09:36:27Z)
• SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection [55.54007781679915]
  We propose Synergistic Semantic-Visual Prompting (SSVP), that efficiently fuses diverse visual encodings to elevate model's fine-grained perception.<n>SSVP achieves state-of-the-art performance with 93.0% Image-AUROC and 92.2% Pixel-AUROC on MVTec-AD, significantly outperforming existing zero-shot approaches.
  arXiv  Detail & Related papers  (2026-01-14T04:42:19Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection [50.343419243749054]
  Anomaly detection is critical in fields such as medical diagnostics and industrial defect detection.<n> CLIP's coarse-grained image-text alignment limits localization and detection performance for fine-grained anomalies.<n>Crane improves the state-of-the-art ZSAD from 2% to 28%, at both image and pixel levels, while remaining competitive in inference speed.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• Exploring the Relationship between Samples and Masks for Robust Defect Localization [1.90365714903665]
  This paper proposes a one-stage framework that detects defective patterns directly without the modeling process. Explicit information that could indicate the position of defects is intentionally excluded to avoid learning any direct mapping. Results show that the proposed method is 2.9% higher than the SOTA methods in F1-Score, while substantially outperforming SOTA methods in generalizability.
  arXiv  Detail & Related papers  (2023-06-19T06:41:19Z)
• Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [85.53263670166304]
  One-stage detector basically formulates object detection as dense classification and localization. Recent trend for one-stage detectors is to introduce an individual prediction branch to estimate the quality of localization. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization.
  arXiv  Detail & Related papers  (2020-06-08T07:24:33Z)

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.