VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/sgstq0811/VerdictAD-Jev-AD
Terminology
Sources
- Deep Nearest Neighbor Anomaly Detection
- Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
- Training Verifiers to Solve Math Word Problems
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences
- Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization
- AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
- JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models
- Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
- INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning
- Can Jev be Your Q or Policy in Reinforcement Learning?
- DINOv2: Learning Robust Visual Features without Supervision
- Optimizing PatchCore for Few/many-shot Anomaly Detection
- DINOv3
- NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
- Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
- Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning
- FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
- Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection
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