Copertina

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Van Assel, Hugues, Ibrahim, Mark, Biancalani, Tommaso, Regev, Aviv, Balestriero, Randall
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
di: Lu, Wenquan, et al.
Pubblicazione: (2025)

Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
di: Van Assel, Hugues, et al.
Pubblicazione: (2026)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
di: Balestriero, Randall, et al.
Pubblicazione: (2025)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
di: Otero, Daniel, et al.
Pubblicazione: (2024)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
di: Hsu, Chia-Hong, et al.
Pubblicazione: (2026)

Learning by Reconstruction Produces Uninformative Features For Perception
di: Balestriero, Randall, et al.
Pubblicazione: (2024)

Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
di: Kuang, Yilun, et al.
Pubblicazione: (2026)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
di: Feizi, Aarash, et al.
Pubblicazione: (2024)

Joint-Embedding Predictive Architecture for Self-Supervised Learning of Mask Classification Architecture
di: Kim, Dong-Hee, et al.
Pubblicazione: (2024)

Self-Supervised Learning with a Multi-Task Latent Space Objective
di: De Plaen, Pierre-François, et al.
Pubblicazione: (2026)

A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
di: Terver, Basile, et al.
Pubblicazione: (2026)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
di: Ibrahim, Mark, et al.
Pubblicazione: (2024)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
di: Balestriero, Randall, et al.
Pubblicazione: (2025)

DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
di: Rodas, Bryan, et al.
Pubblicazione: (2025)

Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud
di: Saito, Ayumu, et al.
Pubblicazione: (2024)

Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps
di: Xia, Xue, et al.
Pubblicazione: (2024)

VISReg: Variance-Invariance-Sketching Regularization for JEPA training
di: Wu, Haiyu, et al.
Pubblicazione: (2026)

Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection
di: Zhu, Haoran, et al.
Pubblicazione: (2025)

3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
di: Hu, Naiwen, et al.
Pubblicazione: (2024)

stable-pretraining-v1: Foundation Model Research Made Simple
di: Balestriero, Randall, et al.
Pubblicazione: (2025)

On the Geometry of Deep Learning
di: Balestriero, Randall, et al.
Pubblicazione: (2024)

JointMotion: Joint Self-Supervision for Joint Motion Prediction
di: Wagner, Royden, et al.
Pubblicazione: (2024)

Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture
di: Li, Weijie, et al.
Pubblicazione: (2023)

Joint Supervised and Self-supervised Learning for MRI Reconstruction
di: Yiasemis, George, et al.
Pubblicazione: (2023)

CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture
di: Kalapos, András, et al.
Pubblicazione: (2024)

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles
di: Daniel, Tal, et al.
Pubblicazione: (2023)

S-JEA: Stacked Joint Embedding Architectures for Self-Supervised Visual Representation Learning
di: Manová, Alžběta, et al.
Pubblicazione: (2023)

Self Supervised Networks for Learning Latent Space Representations of Human Body Scans and Motions
di: Hartman, Emmanuel, et al.
Pubblicazione: (2024)

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
di: Al-Tahan, Haider, et al.
Pubblicazione: (2024)

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
di: Sobal, Vlad, et al.
Pubblicazione: (2024)

Self-Supervised Learning for Endoscopic Video Analysis
di: Hirsch, Roy, et al.
Pubblicazione: (2023)

Beyond and Free from Diffusion: Invertible Guided Consistency Training
di: Hsu, Chia-Hong, et al.
Pubblicazione: (2025)

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations
di: Bisulco, Anthony, et al.
Pubblicazione: (2025)

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
di: Gui, Ming, et al.
Pubblicazione: (2025)

Understanding the Detrimental Class-level Effects of Data Augmentation
di: Kirichenko, Polina, et al.
Pubblicazione: (2023)

Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion
di: Tang, Yingzhi, et al.
Pubblicazione: (2026)

Beyond the Noise: Aligning Prompts with Latent Representations in Diffusion Models
di: Ramos, Vasco, et al.
Pubblicazione: (2025)

Deep Networks Always Grok and Here is Why
di: Humayun, Ahmed Imtiaz, et al.
Pubblicazione: (2024)

Hybrid Learning: A Novel Combination of Self-Supervised and Supervised Learning for Joint MRI Reconstruction and Denoising in Low-Field MRI
di: Pei, Haoyang, et al.
Pubblicazione: (2025)

Latent Beam Diffusion Models for Generating Visual Sequences
di: Fernandes, Guilherme, et al.
Pubblicazione: (2025)