Duo Liu

FinerDedup: Sifting Fingerprints for Efficient Data Deduplication on Mobile Devices

2024

Data deduplication is promised to extend the lifetime and capacity of storage on mobile devices. However, existing data deduplication works show high memory consumption and indexing costs for maintaining a fingerprint for each data block, …

Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularization

2025 · arXiv (Cornell University)

Generalized Category Discovery (GCD) aims to identify unlabeled samples by leveraging the base knowledge from labeled ones, where the unlabeled set consists of both base and novel classes. Since clustering methods are time-consuming at inference, …