Efficient Large-Scale Visual Representation Learning And Evaluation
- URL: http://arxiv.org/abs/2305.13399v5
- Date: Tue, 1 Aug 2023 21:01:04 GMT
- Title: Efficient Large-Scale Visual Representation Learning And Evaluation
- Authors: Eden Dolev, Alaa Awad, Denisa Roberts, Zahra Ebrahimzadeh, Marcin
Mejran, Vaibhav Malpani, and Mahir Yavuz
- Abstract summary: We describe challenges in e-commerce vision applications at scale and highlight methods to efficiently train, evaluate, and serve visual representations.
We present ablation studies evaluating visual representations in several downstream tasks.
We include online results from deployed machine learning systems in production on a large scale e-commerce platform.
- Score: 0.13192560874022083
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Efficiently learning visual representations of items is vital for large-scale
recommendations. In this article we compare several pretrained efficient
backbone architectures, both in the convolutional neural network (CNN) and in
the vision transformer (ViT) family. We describe challenges in e-commerce
vision applications at scale and highlight methods to efficiently train,
evaluate, and serve visual representations. We present ablation studies
evaluating visual representations in several downstream tasks. To this end, we
present a novel multilingual text-to-image generative offline evaluation method
for visually similar recommendation systems. Finally, we include online results
from deployed machine learning systems in production on a large scale
e-commerce platform.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.