Image de couverture de livre

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bisulco, Anthony, Ramesh, Rahul, Balestriero, Randall, Chaudhari, Pratik
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Many Perception Tasks are Highly Redundant Functions of their Input Data
par: Ramesh, Rahul, et autres
Publié: (2024)

From NeRFs to Gaussian Splats, and Back
par: He, Siming, et autres
Publié: (2024)

Beyond [cls]: Exploring the true potential of Masked Image Modeling representations
par: Przewięźlikowski, Marcin, et autres
Publié: (2024)

VISReg: Variance-Invariance-Sketching Regularization for JEPA training
par: Wu, Haiyu, et autres
Publié: (2026)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
par: Hsu, Chia-Hong, et autres
Publié: (2026)

Neurosim: A Fast Simulator for Neuromorphic Robot Perception
par: Das, Richeek, et autres
Publié: (2026)

i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
par: Zhang, Kevin, et autres
Publié: (2022)

Beyond and Free from Diffusion: Invertible Guided Consistency Training
par: Hsu, Chia-Hong, et autres
Publié: (2025)

Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
par: Xia, Xue, et autres
Publié: (2024)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
par: Balestriero, Randall, et autres
Publié: (2025)

Learning by Reconstruction Produces Uninformative Features For Perception
par: Balestriero, Randall, et autres
Publié: (2024)

VR-based generation of photorealistic synthetic data for training hand-object tracking models
par: Zhang, Chengyan, et autres
Publié: (2024)

Masked Capsule Autoencoders
par: Everett, Miles, et autres
Publié: (2024)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
par: Balestriero, Randall, et autres
Publié: (2025)

Improving Masked Autoencoders by Learning Where to Mask
par: Chen, Haijian, et autres
Publié: (2023)

FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching
par: Jena, Rohit, et autres
Publié: (2024)

Factored Levenberg-Marquardt for Diffeomorphic Image Registration: An efficient optimizer for FireANTs
par: Jena, Rohit, et autres
Publié: (2026)

Active Scout: Multi-Target Tracking Using Neural Radiance Fields in Dense Urban Environments
par: Hsu, Christopher D., et autres
Publié: (2024)

Recurrent Video Masked Autoencoders
par: Zoran, Daniel, et autres
Publié: (2025)

Self-Guided Masked Autoencoder
par: Shin, Jeongwoo, et autres
Publié: (2025)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
par: Otero, Daniel, et autres
Publié: (2024)

Audiovisual Masked Autoencoders
par: Georgescu, Mariana-Iuliana, et autres
Publié: (2022)

How Effective is Pre-training of Large Masked Autoencoders for Downstream Earth Observation Tasks?
par: Sosa, Jose, et autres
Publié: (2024)

Efficient Masked Autoencoders with Self-Consistency
par: Li, Zhaowen, et autres
Publié: (2023)

Masked Autoencoders are Robust Data Augmentors
par: Xu, Haohang, et autres
Publié: (2022)

Rethinking Patch Dependence for Masked Autoencoders
par: Fu, Letian, et autres
Publié: (2024)

Text-Guided Video Masked Autoencoder
par: Fan, David, et autres
Publié: (2024)

NeighborMAE: Exploiting Spatial Dependencies between Neighboring Earth Observation Images in Masked Autoencoders Pretraining
par: Zeng, Liang, et autres
Publié: (2026)

DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
par: Wu, Qiangqiang, et autres
Publié: (2023)

Deep Networks Always Grok and Here is Why
par: Humayun, Ahmed Imtiaz, et autres
Publié: (2024)

On the Geometry of Deep Learning
par: Balestriero, Randall, et autres
Publié: (2024)

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
par: Humayun, Ahmed Imtiaz, et autres
Publié: (2023)

Gaussian Masked Autoencoders
par: Rajasegaran, Jathushan, et autres
Publié: (2025)

MARMOT: Masked Autoencoder for Modeling Transient Imaging
par: Shen, Siyuan, et autres
Publié: (2025)

Contrastive Masked Autoencoders are Stronger Vision Learners
par: Huang, Zhicheng, et autres
Publié: (2022)

R-MAE: Regions Meet Masked Autoencoders
par: Nguyen, Duy-Kien, et autres
Publié: (2023)

Extending Video Masked Autoencoders to 128 frames
par: Gundavarapu, Nitesh Bharadwaj, et autres
Publié: (2024)

MEGA: Masked Generative Autoencoder for Human Mesh Recovery
par: Fiche, Guénolé, et autres
Publié: (2024)

Masked Autoencoders are Parameter-Efficient Federated Continual Learners
par: He, Yuchen, et autres
Publié: (2024)

Masked Angle-Aware Autoencoder for Remote Sensing Images
par: Li, Zhihao, et autres
Publié: (2024)