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

• URL: http://arxiv.org/abs/2404.12210v2
• Date: Sat, 25 May 2024 14:59:27 GMT
• Title: An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training
• Authors: Jin Gao, Shubo Lin, Shaoru Wang, Yutong Kou, Zeming Li, Liang Li, Congxuan Zhang, Xiaoqin Zhang, Yizheng Wang, Weiming Hu,
• Abstract summary: 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 textitextremely simple lightweight ViTs' fine-tuning performance can also benefit from this pre-training paradigm. 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-1
• Score: 51.622652121580394
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 \textit{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.

Related papers

• How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks? [9.515532265294187]
  Self-supervised pre-training has proven highly effective for many computer vision tasks. It remains unclear under which conditions pre-trained models offer significant advantages over training from scratch.
  arXiv  Detail & Related papers  (2024-09-27T08:15:14Z)
• ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts [52.1635661239108]
  We introduce ExPLoRA, a highly effective technique to improve transfer learning of pre-trained vision transformers (ViTs) under domain shifts. Our experiments demonstrate state-of-the-art results on satellite imagery, even outperforming fully pre-training and fine-tuning ViTs.
  arXiv  Detail & Related papers  (2024-06-16T15:14:56Z)
• Hierarchical Side-Tuning for Vision Transformers [33.536948382414316]
  Fine-tuning pre-trained Vision Transformers (ViTs) has showcased significant promise in enhancing visual recognition tasks. PETL has shown potential for achieving high performance with fewer parameter updates compared to full fine-tuning. This paper introduces Hierarchical Side-Tuning (HST), an innovative PETL method facilitating the transfer of ViT models to diverse downstream tasks.
  arXiv  Detail & Related papers  (2023-10-09T04:16:35Z)
• Instruction Tuned Models are Quick Learners [20.771930945083994]
  In this work, we demonstrate the sample efficiency of instruction tuned models over various tasks. In the STL setting, instruction tuned models equipped with 25% of the downstream train data surpass the SOTA performance on the downstream tasks. In the MTL setting, an instruction tuned model trained on only 6% of downstream training data achieve SOTA, while using 100% of the training data results in a 3.69% points improvement.
  arXiv  Detail & Related papers  (2023-05-17T22:30:01Z)
• Strong Baselines for Parameter Efficient Few-Shot Fine-tuning [50.83426196335385]
  Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer's parameters.
  arXiv  Detail & Related papers  (2023-04-04T16:14:39Z)
• TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models [31.16595289223858]
  Masked image modeling (MIM) performs strongly in pre-training large vision Transformers (ViTs) However, small models that are critical for real-world applications cannot or only marginally benefit from this pre-training approach. We explore distillation techniques to transfer the success of large MIM-based pre-trained models to smaller ones.
  arXiv  Detail & Related papers  (2023-01-03T18:59:54Z)
• Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [56.87383229709899]
  We develop an information rectification module (IRM) and a distribution guided distillation scheme for fully quantized vision transformers (Q-ViT) Our method achieves a much better performance than the prior arts.
  arXiv  Detail & Related papers  (2022-10-13T04:00:29Z)
• A Closer Look at Self-Supervised Lightweight Vision Transformers [44.44888945683147]
  Self-supervised learning on large-scale Vision Transformers (ViTs) as pre-training methods has achieved promising downstream performance. We benchmark several self-supervised pre-training methods on image classification tasks and some downstream dense prediction tasks. Even vanilla lightweight ViTs show comparable performance to previous SOTA networks with delicate architecture design.
  arXiv  Detail & Related papers  (2022-05-28T14:14:57Z)
• When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [111.44860506703307]
  Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures. This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference. We show that the improved robustness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
  arXiv  Detail & Related papers  (2021-06-03T02:08:03Z)

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.