VICE: Variational Interpretable Concept Embeddings

VICE: Variational Interpretable Concept Embeddings

2 May 2022

Lukas Muttenthaler

Patrick McClure

Robert A. Vandermeulen

Francisco Câmara Pereira

Papers citing "VICE: Variational Interpretable Concept Embeddings"

10 / 10 papers shown

Title
Dimensions underlying the representational alignment of deep neural networks with humans F. Mahner Lukas Muttenthaler Umut Güçlü M. Hebart 48 4 0 28 Jan 2025
Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks Teresa Dorszewski Lenka Tětková Lorenz Linhardt Lars Kai Hansen HAI 36 0 0 10 Sep 2024
CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations Chen Wei Jiachen Zou Dietmar Heinke Quanying Liu 48 3 0 25 Apr 2024
An Analysis of Human Alignment of Latent Diffusion Models Lorenz Linhardt Marco Morik Sidney Bender Naima Elosegui Borras DiffM 36 3 0 13 Mar 2024
Getting aligned on representational alignment Ilia Sucholutsky Lukas Muttenthaler Adrian Weller Andi Peng Andreea Bobu ... Thomas Unterthiner Andrew Kyle Lampinen Klaus-Robert Muller M. Toneva Thomas L. Griffiths 64 74 0 18 Oct 2023
Set Learning for Accurate and Calibrated Models Lukas Muttenthaler Robert A. Vandermeulen Qiuyi Zhang Thomas Unterthiner Klaus-Robert Muller 34 2 0 05 Jul 2023
Improving neural network representations using human similarity judgments Lukas Muttenthaler Lorenz Linhardt Jonas Dippel Robert A. Vandermeulen Katherine L. Hermann Andrew Kyle Lampinen Simon Kornblith 40 29 0 07 Jun 2023
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks Lorenz Linhardt Klaus-Robert Muller G. Montavon AAML 26 7 0 12 Apr 2023
When are Post-hoc Conceptual Explanations Identifiable? Tobias Leemann Michael Kirchhof Yao Rong Enkelejda Kasneci Gjergji Kasneci 50 10 0 28 Jun 2022
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,138 0 06 Jun 2015