Enregistré dans:
Détails bibliographiques
Auteurs principaux: Harun, Md Yousuf, Lee, Kyungbok, Gallardo, Jhair, Krishnan, Giri, Kanan, Christopher
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.15018
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917815356751872
author Harun, Md Yousuf
Lee, Kyungbok
Gallardo, Jhair
Krishnan, Giri
Kanan, Christopher
author_facet Harun, Md Yousuf
Lee, Kyungbok
Gallardo, Jhair
Krishnan, Giri
Kanan, Christopher
contents Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing transferability and out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which is closely related to intermediate neural collapse. This hypothesis suggests that deeper DNN layers compress representations and hinder OOD generalization. Contrary to earlier work, our experiments show this is not a universal phenomenon. We comprehensively investigate the impact of DNN architecture, training data, image resolution, and augmentations on transferability. We identify that training with high-resolution datasets containing many classes greatly reduces representation compression and improves transferability. Our results emphasize the danger of generalizing findings from toy datasets to broader contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15018
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
Harun, Md Yousuf
Lee, Kyungbok
Gallardo, Jhair
Krishnan, Giri
Kanan, Christopher
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing transferability and out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which is closely related to intermediate neural collapse. This hypothesis suggests that deeper DNN layers compress representations and hinder OOD generalization. Contrary to earlier work, our experiments show this is not a universal phenomenon. We comprehensively investigate the impact of DNN architecture, training data, image resolution, and augmentations on transferability. We identify that training with high-resolution datasets containing many classes greatly reduces representation compression and improves transferability. Our results emphasize the danger of generalizing findings from toy datasets to broader contexts.
title What Variables Affect Out-of-Distribution Generalization in Pretrained Models?
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.15018