Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning

27 June 2022

Pascal Vincent

Papers citing "Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning"

20 / 20 papers shown

Title
An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research Patrik Reizinger Randall Balestriero David Klindt Wieland Brendel 36 0 0 17 Apr 2025
Perception Encoder: The best visual embeddings are not at the output of the network Daniel Bolya Po-Yao (Bernie) Huang Peize Sun Jang Hyun Cho Andrea Madotto ... Shiyu Dong Nikhila Ravi Daniel Li Piotr Dollár Christoph Feichtenhofer ObjD VOS 103 0 0 17 Apr 2025
Does Representation Matter? Exploring Intermediate Layers in Large Language Models Oscar Skean Md Rifat Arefin Yann LeCun Ravid Shwartz-Ziv 79 7 0 12 Dec 2024
Beyond [cls]: Exploring the true potential of Masked Image Modeling representations Marcin Przewiȩźlikowski Randall Balestriero Wojciech Jasiński Marek 'Smieja Bartosz Zieliñski 59 0 0 04 Dec 2024
Cross-Entropy Is All You Need To Invert the Data Generating Process Patrik Reizinger Alice Bizeul Attila Juhos Julia E. Vogt Randall Balestriero Wieland Brendel David Klindt SSL OOD BDL DRL 76 3 0 29 Oct 2024
Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex Alex Mulrooney Austin J. Brockmeier 41 0 0 08 Oct 2024
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning Grzegorz Rype'sć Sebastian Cygert Tomasz Trzciñski Bartłomiej Twardowski 30 4 0 26 Sep 2024
A deep cut into Split Federated Self-supervised Learning Marcin Przewiȩźlikowski Marcin Osial Bartosz Zieliñski Marek 'Smieja FedML 38 0 0 12 Jun 2024
ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations Sravanti Addepalli Priyam Dey R. Venkatesh Babu 26 0 0 09 Jun 2024
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation Kimia Hamidieh Haoran Zhang Swami Sankaranarayanan Marzyeh Ghassemi 38 0 0 28 May 2024
Investigating the Benefits of Projection Head for Representation Learning Yihao Xue Eric Gan Jiayi Ni Siddharth Joshi Baharan Mirzasoleiman 29 10 0 18 Mar 2024
Revisiting Supervision for Continual Representation Learning Daniel Marczak Sebastian Cygert Tomasz Trzciñski Bartlomiej Twardowski SSL CLL 26 0 0 22 Nov 2023
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery Grzegorz Rype'sć Daniel Marczak Sebastian Cygert Tomasz Trzciñski Bartlomiej Twardowski VLM CLL 28 2 0 23 Aug 2023
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning Borja Rodríguez Gálvez Arno Blaas P. Rodríguez Adam Goliñski Xavier Suau Jason Ramapuram Dan Busbridge Luca Zappella 14 6 0 20 Jul 2023
Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning Nicolas Michel Giovanni Chierchia Romain Negrel J. Bercher 6 2 0 06 Jun 2023
Augmentation-aware Self-supervised Learning with Conditioned Projector Marcin Przewike'zlikowski Mateusz Pyla Bartosz Zieliñski Bartlomiej Twardowski Jacek Tabor Marek Śmieja SSL 19 2 0 31 May 2023
Compressive Visual Representations Kuang-Huei Lee Anurag Arnab S. Guadarrama John F. Canny Ian S. Fischer SSL 57 48 0 27 Sep 2021
Emerging Properties in Self-Supervised Vision Transformers Mathilde Caron Hugo Touvron Ishan Misra Hervé Jégou Julien Mairal Piotr Bojanowski Armand Joulin 295 5,761 0 29 Apr 2021
Scaling Down Deep Learning with MNIST-1D S. Greydanus Dmitry Kobak 6 20 0 29 Nov 2020
Improved Baselines with Momentum Contrastive Learning Xinlei Chen Haoqi Fan Ross B. Girshick Kaiming He SSL 238 3,359 0 09 Mar 2020