SeiT++: Masked Token Modeling Improves Storage-efficient Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Minhyun, Park, Song, Heo, Byeongho, Han, Dongyoon, Shim, Hyunjung
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916351843500032
author Lee, Minhyun
Park, Song
Heo, Byeongho
Han, Dongyoon
Shim, Hyunjung
author_facet Lee, Minhyun
Park, Song
Heo, Byeongho
Han, Dongyoon
Shim, Hyunjung
contents Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting in significant storage requirements. This storage challenge is a critical bottleneck for scaling up models. A recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i.e., tokens) as network inputs for vision classification. This approach achieved 90% of the performance of a model trained on full-pixel images with only 1% of the storage. While SeiT needs labeled data, its potential in scenarios beyond fully supervised learning remains largely untapped. In this paper, we extend SeiT by integrating Masked Token Modeling (MTM) for self-supervised pre-training. Recognizing that self-supervised approaches often demand more data due to the lack of labels, we introduce TokenAdapt and ColorAdapt. These methods facilitate comprehensive token-friendly data augmentation, effectively addressing the increased data requirements of self-supervised learning. We evaluate our approach across various scenarios, including storage-efficient ImageNet-1k classification, fine-grained classification, ADE-20k semantic segmentation, and robustness benchmarks. Experimental results demonstrate consistent performance improvement in diverse experiments, validating the effectiveness of our method. Code is available at https://github.com/naver-ai/seit.
format Preprint
id arxiv_https___arxiv_org_abs_2312_10105
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SeiT++: Masked Token Modeling Improves Storage-efficient Training
Lee, Minhyun
Park, Song
Heo, Byeongho
Han, Dongyoon
Shim, Hyunjung
Computer Vision and Pattern Recognition
Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting in significant storage requirements. This storage challenge is a critical bottleneck for scaling up models. A recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i.e., tokens) as network inputs for vision classification. This approach achieved 90% of the performance of a model trained on full-pixel images with only 1% of the storage. While SeiT needs labeled data, its potential in scenarios beyond fully supervised learning remains largely untapped. In this paper, we extend SeiT by integrating Masked Token Modeling (MTM) for self-supervised pre-training. Recognizing that self-supervised approaches often demand more data due to the lack of labels, we introduce TokenAdapt and ColorAdapt. These methods facilitate comprehensive token-friendly data augmentation, effectively addressing the increased data requirements of self-supervised learning. We evaluate our approach across various scenarios, including storage-efficient ImageNet-1k classification, fine-grained classification, ADE-20k semantic segmentation, and robustness benchmarks. Experimental results demonstrate consistent performance improvement in diverse experiments, validating the effectiveness of our method. Code is available at https://github.com/naver-ai/seit.
title SeiT++: Masked Token Modeling Improves Storage-efficient Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.10105