Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance

13 October 2021

Papers citing "Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance"

6 / 6 papers shown

Title
Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer Enming Zhang Liwen Cao Yanru Wu Zijie Zhao Guan Wang Yang Li 45 0 0 09 Apr 2025
Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs Kaichao You Yong Liu Ziyang Zhang Jianmin Wang Michael I. Jordan Mingsheng Long 95 30 0 20 Oct 2021
A linearized framework and a new benchmark for model selection for fine-tuning Aditya Deshpande Alessandro Achille Avinash Ravichandran Hao Li L. Zancato Charless C. Fowlkes Rahul Bhotika Stefano Soatto Pietro Perona ALM 105 37 0 29 Jan 2021
Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddings Benedek Rozemberczki Rik Sarkar 101 52 0 08 Jan 2021
Multi-scale Attributed Node Embedding Benedek Rozemberczki Carl Allen Rik Sarkar GNN 139 828 0 28 Sep 2019
Transferability and Hardness of Supervised Classification Tasks Anh Tran Cuong V Nguyen Tal Hassner 134 163 0 21 Aug 2019