Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

8 June 2021

Wieland Brendel

Francesco Locatello

Papers citing "Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style"

33 / 83 papers shown

Title
Robust Self-Supervised Learning with Lie Groups Mark Ibrahim Diane Bouchacourt Ari S. Morcos SSL OOD 38 6 0 24 Oct 2022
A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning Guozheng Ma Zhen Wang Zhecheng Yuan Xueqian Wang Bo Yuan Dacheng Tao OffRL 35 26 0 10 Oct 2022
Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content! Stefan Smeu Elena Burceanu Andrei Liviu Nicolicioiu Emanuela Haller 35 4 0 06 Oct 2022
What shapes the loss landscape of self-supervised learning? Liu Ziyin Ekdeep Singh Lubana Masakuni Ueda Hidenori Tanaka 50 20 0 02 Oct 2022
On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning T. Pham Chaoning Zhang Axi Niu Kang Zhang Chang D. Yoo 36 11 0 11 Aug 2022
Analyzing Data-Centric Properties for Graph Contrastive Learning Puja Trivedi Ekdeep Singh Lubana Mark Heimann Danai Koutra Jayaraman J. Thiagarajan 30 11 0 04 Aug 2022
On the Strong Correlation Between Model Invariance and Generalization Weijian Deng Stephen Gould Liang Zheng OOD 32 16 0 14 Jul 2022
Pixel-level Correspondence for Self-Supervised Learning from Video Yash Sharma Yi Zhu Chris Russell Thomas Brox SSL 20 4 0 08 Jul 2022
Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning Damien Teney Maxime Peyrard Ehsan Abbasnejad 35 29 0 06 Jul 2022
Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis Ronan Perry Julius von Kügelgen Bernhard Schölkopf 41 48 0 04 Jun 2022
Weakly Supervised Representation Learning with Sparse Perturbations Kartik Ahuja Jason S. Hartford Yoshua Bengio SSL 35 58 0 02 Jun 2022
The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning Zixin Wen Yuanzhi Li SSL 27 34 0 12 May 2022
Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images P. Jain Bianca Schoen-Phelan R. Ross 27 32 0 04 May 2022
Do More Negative Samples Necessarily Hurt in Contrastive Learning? Pranjal Awasthi Nishanth Dikkala Pritish Kamath 32 40 0 03 May 2022
From Statistical to Causal Learning Bernhard Schölkopf Julius von Kügelgen CML 30 45 0 01 Apr 2022
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition Jun Kimata Tomoya Nitta Toru Tamaki 29 10 0 01 Apr 2022
Weakly supervised causal representation learning Johann Brehmer P. D. Haan Phillip Lippe Taco S. Cohen OOD CML 33 120 0 30 Mar 2022
Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features N. Kalibhat Kanika Narang Hamed Firooz Maziar Sanjabi S. Feizi SSL 38 7 0 03 Mar 2022
Understanding Contrastive Learning Requires Incorporating Inductive Biases Nikunj Saunshi Jordan T. Ash Surbhi Goel Dipendra Kumar Misra Cyril Zhang Sanjeev Arora Sham Kakade A. Krishnamurthy SSL 24 109 0 28 Feb 2022
Sample Efficiency of Data Augmentation Consistency Regularization Shuo Yang Yijun Dong Rachel A. Ward Inderjit S. Dhillon Sujay Sanghavi Qi Lei AAML 23 17 0 24 Feb 2022
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective" Shubhangi Ghosh Luigi Gresele Julius von Kügelgen M. Besserve Bernhard Schölkopf CML 17 0 0 14 Feb 2022
CITRIS: Causal Identifiability from Temporal Intervened Sequences Phillip Lippe Sara Magliacane Sindy Lowe Yuki M. Asano Taco S. Cohen E. Gavves CML 43 101 0 07 Feb 2022
Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases I. Mason Sebastian Starke Taku Komura 3DH 43 47 0 12 Jan 2022
Weakly-Supervised Video Object Grounding via Causal Intervention Wei Wang Junyu Gao Changsheng Xu CML 30 20 0 01 Dec 2021
FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection Nikolaos Dionelis Mehrdad Yaghoobi Sotirios A. Tsaftaris OODD 19 4 0 30 Nov 2021
Identifiable Deep Generative Models via Sparse Decoding Gemma E. Moran Dhanya Sridhar Yixin Wang David M. Blei BDL 31 45 0 20 Oct 2021
On the Surrogate Gap between Contrastive and Supervised Losses Han Bao Yoshihiro Nagano Kento Nozawa SSL UQCV 41 19 0 06 Oct 2021
Socially Supervised Representation Learning: the Role of Subjectivity in Learning Efficient Representations Julius Taylor Eleni Nisioti Clément Moulin-Frier 16 0 0 20 Sep 2021
Contrastive Learning Inverts the Data Generating Process Roland S. Zimmermann Yash Sharma Steffen Schneider Matthias Bethge Wieland Brendel SSL 238 207 0 17 Feb 2021
Understanding self-supervised Learning Dynamics without Contrastive Pairs Yuandong Tian Xinlei Chen Surya Ganguli SSL 138 281 0 12 Feb 2021
Weakly-Supervised Disentanglement Without Compromises Francesco Locatello Ben Poole Gunnar Rätsch Bernhard Schölkopf Olivier Bachem Michael Tschannen CoGe OOD DRL 184 313 0 07 Feb 2020
Multi-task self-supervised learning for Robust Speech Recognition Mirco Ravanelli Jianyuan Zhong Santiago Pascual P. Swietojanski João Monteiro J. Trmal Yoshua Bengio SSL 189 288 0 25 Jan 2020
Building machines that adapt and compute like brains Brenden Lake J. Tenenbaum AI4CE FedML NAI AILaw 254 890 0 11 Nov 2017