AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

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

Minhyun Lee, Song Park, Byeongho Heo, Dongyoon Han, Hyunjung Shim

ECCV 2024 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add masked token modeling pretraining on top of augmentations (ablation)SeiT++ · ImageNet-1k (1.4 GB)top-1 accuracy (%): 75.5 -> 77.8Improved
add masked token modeling to original SeiT (ablation)SeiT · ImageNet-1k (1.4 GB)top-1 accuracy (%): 74.0 -> 75.1Improved
add MTM at the smallest storage budget (ablation)SeiT++ · ImageNet-1k (0.3 GB)top-1 accuracy (%): 51.2 -> 60.6Improved
add ColorAdapt to SeiT (ablation)SeiT · ImageNet-100top-1 accuracy (%): 77.3 -> 78.3Improved
add TokenAdapt to SeiT (ablation)SeiT · ImageNet-100top-1 accuracy (%): 77.3 -> 80.4Improved
combine TokenAdapt and ColorAdapt (ablation)SeiT · ImageNet-100top-1 accuracy (%): 77.3 -> 81.4Improved
use learned TokenAdapt module instead of decode-augment-reencode pipeline (ablation)SeiT · ImageNet-100 (ViT-S)top-1 accuracy (%): 80.1 -> 81.4Improved
reduce TokenAdapt training data to 100 images (ablation)TokenAdapt · ImageNet-1ktop-1 accuracy (%): 75.5 -> 75.1No clear effect
apply token augmentations to robustness evaluationSeiT · ImageNet-C Gaussian noisetop-1 accuracy (%): 50.7 -> 58.6Improved
apply SeiT++ to alternative tokenizers and DCT input (ablation)SeiT · ImageNet-100top-1 accuracy (%): 81.8 -> 83.9 (VQGAN), 69.5 -> 71.0 (DCT)Improved
reduce training images in data-scarce regimeSeiT++ · ImageNet-100 (13k images)top-1 accuracy (%): 43.2 -> 52.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy