Lei Qi

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

2022 · arXiv (Cornell University)

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore …

Efficient Medical Image Assessment via Self-supervised Learning

2022 · arXiv (Cornell University)

High-performance deep learning methods typically rely on large annotated training datasets, which are difficult to obtain in many clinical applications due to the high cost of medical image labeling. Existing data assessment methods commonly require …

NormAUG: Normalization-guided Augmentation for Domain Generalization

2023 · arXiv (Cornell University)

Deep learning has made significant advancements in supervised learning. However, models trained in this setting often face challenges due to domain shift between training and test sets, resulting in a significant drop in performance during …

PLACE Dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization

2023 · ACM Transactions on Multimedia Computing Communications and Applications

Domain generalization (DG) aims to learn a generic model from multiple observed source domains that generalizes well to arbitrary unseen target domains without further training. The major challenge in DG is that the model inevitably …

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

2025

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but have limitations: relying …