Výsledky vyhledávání

Report

Cascade Prompt Learning for Vision-Language Model Adaptation

Autor: Wu, Ge, Zhang, Xin, Li, Zheng, Chen, Zhaowei, Liang, Jiajun, Yang, Jian, Li, Xiang

Prompt learning has surfaced as an effective approach to enhance the performance of Vision-Language Models (VLMs) like CLIP when applied to downstream tasks. However, current learnable prompt tokens are primarily used for the single phase of adapting

Externí odkaz: http://arxiv.org/abs/2409.17805

Zobrazit plný text záznamu

Report

Blockchain-based Privacy-Preserving Public Key Searchable Encryption with Strong Traceability

Autor: Han, Yue, Han, Jinguang, Meng, Weizhi, Lai, Jianchang, Wu, Ge

Public key searchable encryption (PKSE) scheme allows data users to search over encrypted data. To identify illegal users, many traceable PKSE schemes have been proposed. However, existing schemes cannot trace the keywords which illegal users searche

Externí odkaz: http://arxiv.org/abs/2312.16954

Zobrazit plný text záznamu

Report

A Survey of Historical Learning: Learning Models with Learning History

Autor: Li, Xiang, Wu, Ge, Yang, Lingfeng, Wang, Wenhai, Song, Renjie, Yang, Jian

New knowledge originates from the old. The various types of elements, deposited in the training history, are a large amount of wealth for improving learning deep models. In this survey, we comprehensively review and summarize the topic--``Historical

Externí odkaz: http://arxiv.org/abs/2303.12992

Zobrazit plný text záznamu