Embedding Predictive Adaptation and Refinement for Multi-Modal Industrial Anomaly Detection
cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/ohcoheaj/EPAR
Terminology
Sources
- Deep ViT Features as Dense Visual Descriptors
- VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
- The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
- ShapeNet: An Information-Rich 3D Model Repository
- Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning
- Decoupled Weight Decay Regularization
- What Do Self-Supervised Vision Transformers Learn?
- Multi-Scale Distillation for RGB-D Anomaly Detection on the PD-REAL Dataset
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs