Cover Image

Generation is Required for Data-Efficient Perception

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Brady, Jack, Schölkopf, Bernhard, Kipf, Thomas, Buchholz, Simon, Brendel, Wieland
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interaction Asymmetry: A General Principle for Learning Composable Abstractions
by: Brady, Jack, et al.
Published: (2024)

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
by: Li, Fanfei, et al.
Published: (2025)

RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks
by: Ghosh, Partha, et al.
Published: (2024)

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
by: Mayilvahanan, Prasanna, et al.
Published: (2023)

InfoNCE: Identifying the Gap Between Theory and Practice
by: Rusak, Evgenia, et al.
Published: (2024)

Hyperbolic Busemann Neural Networks
by: Chen, Ziheng, et al.
Published: (2026)

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models
by: Zimmermann, Roland S., et al.
Published: (2023)

Diffusion-Based Representation Learning
by: Mittal, Sarthak, et al.
Published: (2021)

Drifting Fields are not Conservative
by: Franz, Leonard T., et al.
Published: (2026)

Verbalized Machine Learning: Revisiting Machine Learning with Language Models
by: Xiao, Tim Z., et al.
Published: (2024)

Structure by Architecture: Structured Representations without Regularization
by: Leeb, Felix, et al.
Published: (2020)

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
by: Zeller, Jana, et al.
Published: (2026)

GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs
by: Gao, Gege, et al.
Published: (2023)

Ghost on the Shell: An Expressive Representation of General 3D Shapes
by: Liu, Zhen, et al.
Published: (2023)

Cryo-CARE: Content-Aware Image Restoration for Cryo-Transmission Electron Microscopy Data
by: Buchholz, Tim-Oliver, et al.
Published: (2018)

Don't trust your eyes: on the (un)reliability of feature visualizations
by: Geirhos, Robert, et al.
Published: (2023)

Direct Motion Models for Assessing Generated Videos
by: Allen, Kelsey, et al.
Published: (2025)

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
by: Eastwood, Cian, et al.
Published: (2023)

Orthogonal Finetuning Made Scalable
by: Qiu, Zeju, et al.
Published: (2025)

DORSal: Diffusion for Object-centric Representations of Scenes et al
by: Jabri, Allan, et al.
Published: (2023)

DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
by: Chen, Wenlin, et al.
Published: (2025)

From Pixels to Components: Eigenvector Masking for Visual Representation Learning
by: Bizeul, Alice, et al.
Published: (2025)

Opinion: Learning Intuitive Physics May Require More than Visual Data
by: Su, Ellen, et al.
Published: (2025)

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
by: Uselis, Arnas, et al.
Published: (2026)

Generative Latent Diffusion for Efficient Spatiotemporal Data Reduction
by: Li, Xiao, et al.
Published: (2025)

Does Data-Efficient Generalization Exacerbate Bias in Foundation Models?
by: Queiroz, Dilermando, et al.
Published: (2024)

Low-Pass Filtering Improves Behavioral Alignment of Vision Models
by: Wolff, Max, et al.
Published: (2026)

Harnessing Data Asymmetry: Manifold Learning in the Finsler World
by: Dagès, Thomas, et al.
Published: (2026)

Many Perception Tasks are Highly Redundant Functions of their Input Data
by: Ramesh, Rahul, et al.
Published: (2024)

EMPERROR: A Flexible Generative Perception Error Model for Probing Self-Driving Planners
by: Hanselmann, Niklas, et al.
Published: (2024)

When and How Does CLIP Enable Domain and Compositional Generalization?
by: Kempf, Elias, et al.
Published: (2025)

DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
by: Seitzer, Maximilian, et al.
Published: (2023)

Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
by: Güzel, Ahmet H., et al.
Published: (2025)

Efficient Unlearning through Maximizing Relearning Convergence Delay
by: Tran, Khoa, et al.
Published: (2026)

Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification
by: Huseljic, Denis, et al.
Published: (2024)

Latent Diffusion Inversion Requires Understanding the Latent Space
by: Rao, Mingxing, et al.
Published: (2025)

AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
by: Wang, Fu-Yun, et al.
Published: (2024)

Energy-based Hopfield Boosting for Out-of-Distribution Detection
by: Hofmann, Claus, et al.
Published: (2024)

Data-to-Model Distillation: Data-Efficient Learning Framework
by: Sajedi, Ahmad, et al.
Published: (2024)

WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
by: Wang, Haiyu, et al.
Published: (2026)