AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability

Zijian Wang, Yadan Luo, Liang Zheng, Zi Huang, Mahsa Baktashmotlagh

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use neural-collapse-based NCTI instead of SFDA for ranking supervised modelsTransferability estimation · 11 target datasets, supervised modelsaverage weighted Kendall tau: 0.663 -> 0.726Improved
Use NCTI instead of SFDA for ranking self-supervised modelsTransferability estimation · 11 target datasets, self-supervised modelsaverage weighted Kendall tau: 0.708 -> 0.719Improved
Use NCTI instead of SFDA in terms of compute timeTransferability estimation · 11 datasets, running timerunning time: approximately 10x speed upImproved
Add the nearest-centroid term Sncc to the combination (ablation)NCTI · Supervised modelsaverage weighted Kendall tauMixed
Add the nearest-centroid term Sncc to the combination (ablation)NCTI · Supervised and self-supervised combinedaverage weighted Kendall tau: +4.2% absoluteImproved
Combine Sseli with Svc instead of using either alone (ablation)NCTI · Supervised and self-supervised modelsaverage weighted Kendall tauImproved
Use equal weights of 1 for the three terms (ablation)NCTI · 11 datasets, weights 0.1 to 2average tau: tau >= 0.7 for most weight settingsNo clear effect
Reduce target data to few samples per class (ablation)NCTI · SUN397weighted Kendall tauMixed
Compute Svc on source features of pre-training data (ablation)NCTI components · Source subsetweighted Kendall tau: 0.725 (supervised), 0.598 (self-supervised)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy