Visual Representation Learning Does Not Generalize Strongly Within the
Same Domain

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain

17 July 2021

Julius von Kügelgen

Frederik Trauble

Peter V. Gehler

Matthias Bethge

Bernhard Schölkopf

Francesco Locatello

Wieland Brendel

Papers citing "Visual Representation Learning Does Not Generalize Strongly Within the Same Domain"

17 / 17 papers shown

Title
Enhancing deep neural networks through complex-valued representations and Kuramoto synchronization dynamics Sabine Muzellec A. Alamia Thomas Serre Rufin VanRullen 39 0 0 28 Feb 2025
State Combinatorial Generalization In Decision Making With Conditional Diffusion Models Xintong Duan Yutong He Fahim Tajwar Wen-Tse Chen Ruslan Salakhutdinov Jeff Schneider OffRL AI4CE 94 0 0 22 Jan 2025
Zero-Shot Generalization of Vision-Based RL Without Data Augmentation S. Batra Gaurav Sukhatme OffRL DRL 26 1 0 09 Oct 2024
Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models Reza Abbasi M. Rohban M. Baghshah CoGe 38 5 0 08 Jul 2024
When does compositional structure yield compositional generalization? A kernel theory Samuel Lippl Kim Stachenfeld NAI CoGe 65 5 0 26 May 2024
Compositional Generalization from First Principles Thaddäus Wiedemer Prasanna Mayilvahanan Matthias Bethge Wieland Brendel OCL 25 36 0 10 Jul 2023
Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization Tao Yang Yuwang Wang Cuiling Lan Yan Lu Nanning Zheng OCL CoGe DRL 24 7 0 29 May 2023
Distributional Shift Adaptation using Domain-Specific Features Anique Tahir Lu Cheng Ruocheng Guo Huan Liu VLM TTA OOD OODD 20 2 0 09 Nov 2022
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift Yivan Zhang Jindong Wang Xingxu Xie Masashi Sugiyama OOD 29 1 0 03 Aug 2022
Assaying Out-Of-Distribution Generalization in Transfer Learning F. Wenzel Andrea Dittadi Peter V. Gehler Carl-Johann Simon-Gabriel Max Horn ... Chris Russell Thomas Brox Bernt Schiele Bernhard Schölkopf Francesco Locatello OOD OODD AAML 49 71 0 19 Jul 2022
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition Jorge Armando Mendez Mendez Eric Eaton KELM CLL 19 27 0 15 Jul 2022
Identifiability of deep generative models without auxiliary information Bohdan Kivva Goutham Rajendran Pradeep Ravikumar Bryon Aragam DRL 18 48 0 20 Jun 2022
Do Neural Networks for Segmentation Understand Insideness? Kimberly M Villalobos Vilim Štih Amineh Ahmadinejad Shobhita Sundaram Jamell Dozier Andrew Francl Frederico Azevedo Tomotake Sasaki Xavier Boix 32 8 0 25 Jan 2022
DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization Opportunities Elias Eulig Piyapat Saranrittichai Chaithanya Kumar Mummadi K. Rambach William H. Beluch Xiahan Shi Volker Fischer 135 11 0 12 Aug 2021
Exploring the Latent Space of Autoencoders with Interventional Assays Felix Leeb Stefan Bauer M. Besserve Bernhard Schölkopf DRL 41 17 0 30 Jun 2021
On the Binding Problem in Artificial Neural Networks Klaus Greff Sjoerd van Steenkiste Jürgen Schmidhuber OCL 224 254 0 09 Dec 2020
Weakly-Supervised Disentanglement Without Compromises Francesco Locatello Ben Poole Gunnar Rätsch Bernhard Schölkopf Olivier Bachem Michael Tschannen CoGe OOD DRL 173 313 0 07 Feb 2020