Cover Image

Learning by Reconstruction Produces Uninformative Features For Perception

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Balestriero, Randall, LeCun, Yann
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

Fast and Exact Enumeration of Deep Networks Partitions Regions
by: Balestriero, Randall, et al.
Published: (2024)

Blockwise Self-Supervised Learning at Scale
by: Siddiqui, Shoaib Ahmed, et al.
Published: (2023)

Variance-Covariance Regularization Improves Representation Learning
by: Zhu, Jiachen, et al.
Published: (2023)

Revisiting Feature Prediction for Learning Visual Representations from Video
by: Bardes, Adrien, et al.
Published: (2024)

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

Learning and Leveraging World Models in Visual Representation Learning
by: Garrido, Quentin, et al.
Published: (2024)

Navigation World Models
by: Bar, Amir, et al.
Published: (2024)

Transformers without Normalization
by: Zhu, Jiachen, et al.
Published: (2025)

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

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

Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
by: Van Assel, Hugues, et al.
Published: (2025)

Video Representation Learning with Joint-Embedding Predictive Architectures
by: Drozdov, Katrina, et al.
Published: (2024)

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

Whole-Body Conditioned Egocentric Video Prediction
by: Bai, Yutong, et al.
Published: (2025)

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

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

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

A hierarchical loss and its problems when classifying non-hierarchically
by: Wu, Cinna, et al.
Published: (2017)

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed
by: Zhang, Jiaqi, et al.
Published: (2025)

URLOST: Unsupervised Representation Learning without Stationarity or Topology
by: Yun, Zeyu, et al.
Published: (2023)

Stochastic positional embeddings improve masked image modeling
by: Bar, Amir, et al.
Published: (2023)

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
by: Zhai, Yuexiang, et al.
Published: (2024)

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

LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
by: Huang, Hai, et al.
Published: (2025)

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
by: Maes, Lucas, et al.
Published: (2026)

Learning Latent Action World Models In The Wild
by: Garrido, Quentin, et al.
Published: (2026)

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

Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
by: Denton, Remi, et al.
Published: (2014)

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

PooDLe: Pooled and dense self-supervised learning from naturalistic videos
by: Wang, Alex N., et al.
Published: (2024)

Representation Learning for Spatiotemporal Physical Systems
by: Qu, Helen, et al.
Published: (2026)

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
by: Du, Hongyang, et al.
Published: (2026)

Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation
by: Zeevi, Tal, et al.
Published: (2024)

Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
by: Huang, Hai, et al.
Published: (2026)

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
by: Mialon, Grégoire, et al.
Published: (2022)

Hierarchical World Models as Visual Whole-Body Humanoid Controllers
by: Hansen, Nicklas, et al.
Published: (2024)

Feature Expansion and enhanced Compression for Class Incremental Learning
by: Ferdinand, Quentin, et al.
Published: (2024)

Frustratingly Easy Feature Reconstruction for Out-of-Distribution Detection
by: Wang, Yingsheng, et al.
Published: (2025)