34 citations · 84 across the 9 of their papers we have counts for
9 papers
Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
Zhaoxiang Zhang, Hanqiu Deng, Jinan Bao +1
Image Anomaly Detection has been a challenging task in Computer Vision field. The advent of Vision-Language models, particularly the rise of CLIP-based frameworks, has opened new a…
FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discrimination
Yifei Lin, Hanqiu Deng, Xingyu Li
Nowadays large computers extensively output logs to record the runtime status and it has become crucial to identify any suspicious or malicious activities from the information prov…
Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization
Hanqiu Deng, Xingyu Li
Visual anomaly detection is a challenging open-set task aimed at identifying unknown anomalous patterns while modeling normal data. The knowledge distillation paradigm has shown re…
Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization
Hanqiu Deng, Zhaoxiang Zhang, Jinan Bao +1
Contrastive Language-Image Pre-training (CLIP) models have shown promising performance on zero-shot visual recognition tasks by learning visual representations under natural langua…
BMAD: Benchmarks for Medical Anomaly Detection
Jinan Bao, Hanshi Sun, Hanqiu Deng +3
Anomaly detection (AD) is a fundamental research problem in machine learning and computer vision, with practical applications in industrial inspection, video surveillance, and medi…
Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners
Renrui Zhang, Xiangfei Hu, Bohao Li +5
Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown pro…
Biomedical image analysis competitions: The state of current participation practice
Matthias Eisenmann, Annika Reinke, Vivienn Weru +352
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known abou…
Collaboration of Pre-trained Models Makes Better Few-shot Learner
Renrui Zhang, Bohao Li, Wei Zhang +4
Few-shot classification requires deep neural networks to learn generalized representations only from limited training images, which is challenging but significant in low-data regim…
Anomaly Detection via Reverse Distillation from One-Class Embedding
Hanqiu Deng, Xingyu Li
Knowledge distillation (KD) achieves promising results on the challenging problem of unsupervised anomaly detection (AD).The representation discrepancy of anomalies in the teacher-…