Rethinking Patch Dependence for Masked Autoencoders

• URL: http://arxiv.org/abs/2401.14391v2
• Date: Thu, 10 Apr 2025 07:50:15 GMT
• Title: Rethinking Patch Dependence for Masked Autoencoders
• Authors: Letian Fu, Long Lian, Renhao Wang, Baifeng Shi, Xudong Wang, Adam Yala, Trevor Darrell, Alexei A. Efros, Ken Goldberg,
• Abstract summary: We study the impact of inter-patch dependencies in the decoder of masked autoencoders (MAE) on representation learning.<n>We propose a simple visual pretraining framework: cross-attention masked autoencoders (CrossMAE)
• Score: 89.02576415930963
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we examine the impact of inter-patch dependencies in the decoder of masked autoencoders (MAE) on representation learning. We decompose the decoding mechanism for masked reconstruction into self-attention between mask tokens and cross-attention between masked and visible tokens. Our findings reveal that MAE reconstructs coherent images from visible patches not through interactions between patches in the decoder but by learning a global representation within the encoder. This discovery leads us to propose a simple visual pretraining framework: cross-attention masked autoencoders (CrossMAE). This framework employs only cross-attention in the decoder to independently read out reconstructions for a small subset of masked patches from encoder outputs. This approach achieves comparable or superior performance to traditional MAE across models ranging from ViT-S to ViT-H and significantly reduces computational requirements. By its design, CrossMAE challenges the necessity of interaction between mask tokens for effective masked pretraining. Code and models are publicly available: https://crossmae.github.io

Related papers

• Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization [42.82742477950748]
  Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. We introduce the Multi-level Optimized Mask Autoencoder (MLO-MAE), a novel framework that learns an optimal masking strategy during pretraining. Our experimental findings highlight MLO-MAE's significant advancements in visual representation learning.
  arXiv  Detail & Related papers  (2024-02-28T07:37:26Z)
• Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning [18.10704604275133]
  Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for 2D and 3D computer vision. We propose Point Regress AutoEncoder (Point-RAE), a new scheme for regressive autoencoders for point cloud self-supervised learning. Our approach is efficient during pre-training and generalizes well on various downstream tasks.
  arXiv  Detail & Related papers  (2023-09-25T17:23:33Z)
• CL-MAE: Curriculum-Learned Masked Autoencoders [49.24994655813455]
  We propose a curriculum learning approach that updates the masking strategy to continually increase the complexity of the self-supervised reconstruction task. We train our Curriculum-Learned Masked Autoencoder (CL-MAE) on ImageNet and show that it exhibits superior representation learning capabilities compared to MAE.
  arXiv  Detail & Related papers  (2023-08-31T09:13:30Z)
• Siamese Masked Autoencoders [76.35448665609998]
  We present Siamese Masked Autoencoders (SiamMAE) for learning visual correspondence from videos. SiamMAE operates on pairs of randomly sampled video frames and asymmetrically masks them. It outperforms state-of-the-art self-supervised methods on video object segmentation, pose keypoint propagation, and semantic part propagation tasks.
  arXiv  Detail & Related papers  (2023-05-23T17:59:46Z)
• SdAE: Self-distillated Masked Autoencoder [95.3684955370897]
  Self-distillated masked AutoEncoder network SdAE is proposed in this paper. With only 300 epochs pre-training, a vanilla ViT-Base model achieves an 84.1% fine-tuning accuracy on ImageNet-1k classification.
  arXiv  Detail & Related papers  (2022-07-31T15:07:25Z)
• Masked Autoencoders that Listen [79.99280830830854]
  This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers. The decoder then re-orders and decodes the encoded context padded with mask tokens, in order to reconstruct the input spectrogram.
  arXiv  Detail & Related papers  (2022-07-13T17:59:55Z)
• MAE-AST: Masked Autoencoding Audio Spectrogram Transformer [11.814012909512307]
  We propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. We leverage the insight that the SSAST uses a very high masking ratio (75%) during pretraining, meaning that the vast majority of self-attention compute is performed on mask tokens. We find that MAE-like pretraining can provide a 3x speedup and 2x memory usage reduction over the vanilla SSAST.
  arXiv  Detail & Related papers  (2022-03-30T22:06:13Z)
• Context Autoencoder for Self-Supervised Representation Learning [64.63908944426224]
  We pretrain an encoder by making predictions in the encoded representation space. The network is an encoder-regressor-decoder architecture. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks.
  arXiv  Detail & Related papers  (2022-02-07T09:33:45Z)
• 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)
• OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection [1.933681537640272]
  novelty detection is the task of recognizing samples that do not belong to the distribution of the target class. Deep autoencoders have been widely used as a base of many unsupervised novelty detection methods. We have designed a framework consisting of two competing networks, a Mask Module and a Reconstructor.
  arXiv  Detail & Related papers  (2021-03-27T17:59:40Z)

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.