SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

Song Park, Sanghyuk Chun, Byeongho Heo, Wonjae Kim, Sangdoo Yun; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 17248-17259


We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e.g., the LAION-4B dataset needs 240TB storage space). However, it has become challenging to deal with unlimited dataset storage with limited storage infrastructure. A number of storage-efficient training methods have been proposed to tackle the problem, but they are rarely scalable or suffer from severe damage to performance. In this paper, we propose a storage-efficient training strategy for vision classifiers for large-scale datasets (e.g., ImageNet) that only uses 1024 tokens per instance without using the raw level pixels; our token storage only needs <1% of the original JPEG-compressed raw pixels. We also propose token augmentations and a Stem-adaptor module to make our approach able to use the same architecture as pixel-based approaches with only minimal modifications on the stem layer and the carefully tuned optimization settings. Our experimental results on ImageNet-1K show that our method significantly outperforms other storage-efficient training methods with a large gap. We further show the effectiveness of our method in other practical scenarios, storage-efficient pre-training, and continual learning. We will make our implementation and tokenized dataset publicly after the acceptance.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Park_2023_ICCV, author = {Park, Song and Chun, Sanghyuk and Heo, Byeongho and Kim, Wonjae and Yun, Sangdoo}, title = {SeiT: Storage-Efficient Vision Training with Tokens Using 1\% of Pixel Storage}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {17248-17259} }