activity
20242026
collaborators

13 papers

cs.CV2026

Visual Prompt-Agnostic Evolution

Junze Wang, Lei Fan, Dezheng Zhang +5

Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer…

cs.CV2025

Cross-Stain Contrastive Learning for Paired Immunohistochemistry and Histopathology Slide Representation Learning

Yizhi Zhang, Lei Fan, Zhulin Tao +4

Universal, transferable whole-slide image (WSI) representations are central to computational pathology. Incorporating multiple markers (e.g., immunohistochemistry, IHC) alongside H…

cs.CV2025

ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categories

Hai Ling, Jia Guo, Zhulin Tao +6

Anomaly detection (AD) aims to identify defects using normal-only training data. Existing anomaly detection benchmarks (e.g., MVTec-AD with 15 categories) cover only a narrow range…

cs.CV2025

One Dinomaly2 Detect Them All: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection

Jia Guo, Shuai Lu, Lei Fan +9

Unsupervised anomaly detection (UAD) has evolved from building specialized single-class models to unified multi-class models, yet existing multi-class models significantly underper…

cs.CL2025

SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment

Guoxin Zang, Xue Li, Donglin Di +4

While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle in industrial anomaly detection and reasoning, particularly in de…

cs.CV2025

Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detection

Lei Fan, Junjie Huang, Donglin Di +4

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource managem…