paper-with-me

홈 › Papers

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

2022-05-27 · Siyuan Li, Di wu, Fang Wu, Zelin Zang, Stan. Z. Li

Masked image modeling, an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers. Its underlying idea is simple: a portion of the input image is masked out and then reconstructed via a pre-text task. However, the working principle behind MIM is not well explained, and previous studies insist that MIM primarily works for the Transformer family but is incompatible with CNNs. In this work, we observe that MIM essentially teaches the model to learn better middle-order interactions among patches for more generalized feature extraction. We then propose an Architecture-Agnostic Masked Image Modeling framework (A$^2$MIM), which is compatible with both Transformers and CNNs in a unified way. Extensive experiments on popular benchmarks show that A$^2$MIM learns better representations without explicit design and endows the backbone model with the stronger capability to transfer to various downstream tasks.

📄 PDF Abstract BibTeX arXiv:2205.13943

Code (3)

Westlake-AI/A2MIM 공식 구현 pytorch
Westlake-AI/openmixup 공식 구현 pytorch
open-mmlab/mmpretrain pytorch

Tasks

Image ClassificationInstance SegmentationObject DetectionSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing

2024-01-15 · Jakob Hackstein, Gencer Sumbul, Kai Norman Clasen, Begüm Demir

Self-supervised learning through masked autoencoders (MAEs) has recently attracted great attention for remote sensing (RS) image representation learning, and thus embodies a significant potential for content-based image …

Content-Based Image RetrievalImage RetrievalRepresentation LearningRetrieval+1

BIM: Block-Wise Self-Supervised Learning with Masked Image Modeling

2023-11-28 · YiXuan Luo, Mengye Ren, Sai Qian Zhang

Like masked language modeling (MLM) in natural language processing, masked image modeling (MIM) aims to extract valuable insights from image patches to enhance the feature extraction capabilities of the underlying deep n…

Contrastive LearningLanguage ModelingLanguage ModellingMasked Language Modeling+1

Cluster and Predict Latents Patches for Improved Masked Image Modeling

2025-02-12 · Timothée Darcet, Federico Baldassarre, Maxime Oquab, Julien Mairal 외

Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this paper, we systematically analyze target repre…

Representation Learning

Energy-Inspired Self-Supervised Pretraining for Vision Models

2023-02-02 · Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu

Motivated by the fact that forward and backward passes of a deep network naturally form symmetric mappings between input and output representations, we introduce a simple yet effective self-supervised vision model pretra…

ColorizationDecoderDenoisingImage Restoration+1

Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning

2024-02-22 · Johnathan Xie, Yoonho Lee, Annie S. Chen, Chelsea Finn

Self-supervised learning excels in learning representations from large amounts of unlabeled data, demonstrating success across multiple data modalities. Yet, extending self-supervised learning to new modalities is non-tr…

Molecular Property PredictionProperty PredictionSelf-Supervised Learning