Papers › An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked...

An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training

18 Apr 2024arXiv:2404.12210archive 2025-07-28

Jin Gao, Shubo Lin, Shaoru Wang, Yutong Kou, Zeming Li, Liang Li, Congxuan Zhang, Xiaoqin Zhang, Yizheng Wang, Weiming Hu

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the extremely simple lightweight ViTs' fine-tuning performance can also benefit from this pre-training paradigm, which is considerably less studied yet in contrast to the well-established lightweight architecture design methodology. We use an observation-analysis-solution flow for our study. We first systematically observe different behaviors among the evaluated pre-training methods with respect to the downstream fine-tuning data scales. Furthermore, we analyze the layer representation similarities and attention maps across the obtained models, which clearly show the inferior learning of MIM pre-training on higher layers, leading to unsatisfactory transfer performance on data-insufficient downstream tasks. This finding is naturally a guide to designing our distillation strategies during pre-training to solve the above deterioration problem. Extensive experiments have demonstrated the effectiveness of our approach. Our pre-training with distillation on pure lightweight ViTs with vanilla/hierarchical design (5.7M/6.5M) can achieve 79.4%/78.9% top-1 accuracy on ImageNet-1K. It also enables SOTA performance on the ADE20K segmentation task (42.8% mIoU) and LaSOT tracking task (66.1% AUC) in the lightweight regime. The latter even surpasses all the current SOTA lightweight CPU-realtime trackers.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

wangsr126/mae-lite officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningImage ClassificationSemantic SegmentationVisual Tracking

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningMIM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections