Diverse Imagenet Models Transfer Better

Niv Nayman, Avram Golbert, Asaf Noy, Lihi Zelnik-Manor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A commonly accepted hypothesis is that models with higher accuracy on Imagenet perform better on other downstream tasks, leading to much research dedicated to optimizing Imagenet accuracy. Recently this hypothesis has been challenged by evidence showing that self-supervised models transfer better than their supervised counterparts, despite their inferior Imagenet accuracy. This calls for identifying the additional factors, on top of Imagenet accuracy, that make models transferable. In this work we show that high diversity of the filters learnt by the model promotes transferability jointly with Imagenet accuracy. Encouraged by the recent transferability results of self-supervised models, we use a simple procedure to combine self-supervised and supervised pretraining and generate models with both high diversity and high accuracy, and as a result high transferability. We experiment with several architectures and multiple downstream tasks, including both single-label and multi-label classification.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Pages1903-1914
Number of pages12
ISBN (Electronic)9798350318920
DOIs
StatePublished - 2024
Event2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024 - Waikoloa, United States
Duration: 4 Jan 20248 Jan 2024

Publication series

NameProceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024

Conference

Conference2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Country/TerritoryUnited States
CityWaikoloa
Period4/01/248/01/24

Keywords

  • Algorithms
  • Algorithms
  • and algorithms
  • formulations
  • Image recognition and understanding
  • Machine learning architectures

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Diverse Imagenet Models Transfer Better'. Together they form a unique fingerprint.

Cite this