PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling

• URL: http://arxiv.org/abs/2303.02416v2
• Date: Fri, 24 Mar 2023 05:37:41 GMT
• Title: PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling
• Authors: Yuan Liu, Songyang Zhang, Jiacheng Chen, Kai Chen, Dahua Lin
• Abstract summary: Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction. We propose a remarkably simple and effective method, ourmethod, that entails two strategies.
• Score: 83.67628239775878
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT. However, subsequent works have complicated the framework with new auxiliary tasks or extra pre-trained models, inevitably increasing computational overhead. This paper undertakes a fundamental analysis of MIM from the perspective of pixel reconstruction, which examines the input image patches and reconstruction target, and highlights two critical but previously overlooked bottlenecks. Based on this analysis, we propose a remarkably simple and effective method, {\ourmethod}, that entails two strategies: 1) filtering the high-frequency components from the reconstruction target to de-emphasize the network's focus on texture-rich details and 2) adopting a conservative data transform strategy to alleviate the problem of missing foreground in MIM training. {\ourmethod} can be easily integrated into most existing pixel-based MIM approaches (\ie, using raw images as reconstruction target) with negligible additional computation. Without bells and whistles, our method consistently improves three MIM approaches, MAE, ConvMAE, and LSMAE, across various downstream tasks. We believe this effective plug-and-play method will serve as a strong baseline for self-supervised learning and provide insights for future improvements of the MIM framework. Code and models are available at \url{https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/pixmim}.

Related papers

• Symmetric masking strategy enhances the performance of Masked Image Modeling [0.0]
  Masked Image Modeling (MIM) is a technique in self-supervised learning that focuses on acquiring detailed visual representations from unlabeled images. We propose a new masking strategy that effectively helps the model capture global and local features. Based on this masking strategy, SymMIM, our proposed training pipeline for MIM is introduced.
  arXiv  Detail & Related papers  (2024-08-23T00:15:43Z)
• Membership Inference Attack Against Masked Image Modeling [29.699606401861818]
  Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition. In this work, we take a different angle by studying the pre-training data privacy of MIM. We propose the first membership inference attack against image encoders pre-trained by MIM.
  arXiv  Detail & Related papers  (2024-08-13T11:34:28Z)
• CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding [38.53988682814626]
  We propose a context-enhanced masked image modeling method (CtxMIM) for remote sensing image understanding. CtxMIM formulates original image patches as a reconstructive template and employs a Siamese framework to operate on two sets of image patches. With the simple and elegant design, CtxMIM encourages the pre-training model to learn object-level or pixel-level features on a large-scale dataset.
  arXiv  Detail & Related papers  (2023-09-28T18:04:43Z)
• Improving Pixel-based MIM by Reducing Wasted Modeling Capability [77.99468514275185]
  We propose a new method that explicitly utilizes low-level features from shallow layers to aid pixel reconstruction. To the best of our knowledge, we are the first to systematically investigate multi-level feature fusion for isotropic architectures. Our method yields significant performance gains, such as 1.2% on fine-tuning, 2.8% on linear probing, and 2.6% on semantic segmentation.
  arXiv  Detail & Related papers  (2023-08-01T03:44:56Z)
• HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation [5.888156950854715]
  We propose a novel self-supervised pre-training strategy for regressing 3D hand mesh parameters. Our proposed approach, named HandMIM, achieves strong performance on various hand mesh estimation tasks.
  arXiv  Detail & Related papers  (2023-07-29T19:46:06Z)
• Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation [78.13793505707952]
  Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. We propose a novel two-stage framework, which consists of Masked Quantization VAE (MQ-VAE) Stack model from modeling redundancy.
  arXiv  Detail & Related papers  (2023-05-23T02:15:53Z)
• DPPMask: Masked Image Modeling with Determinantal Point Processes [49.65141962357528]
  Masked Image Modeling (MIM) has achieved impressive representative performance with the aim of reconstructing randomly masked images. We show that uniformly random masking widely used in previous works unavoidably loses some key objects and changes original semantic information. To address this issue, we augment MIM with a new masking strategy namely the DPPMask. Our method is simple yet effective and requires no extra learnable parameters when implemented within various frameworks.
  arXiv  Detail & Related papers  (2023-03-13T13:40:39Z)
• Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers [122.01591448013977]
  Masked image modeling (MIM) has demonstrated promising results on downstream tasks. In this paper, we investigate whether there exist other effective ways to learn by recovering missing contents' We summarize a few design principles for token-based pre-training of vision transformers. This design achieves superior performance over MIM in a series of downstream recognition tasks without extra computational cost.
  arXiv  Detail & Related papers  (2022-03-27T14:23:29Z)
• Masked Autoencoders Are Scalable Vision Learners [60.97703494764904]
  Masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. Coupling these two designs enables us to train large models efficiently and effectively.
  arXiv  Detail & Related papers  (2021-11-11T18:46:40Z)

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.