Generative and explainable modeling methods
- Image style transfer using convolutional neural networks (LA Gatys, AS Ecker, M Bethge)
- Texture synthesis using convolutional neural networks (L Gatys, AS Ecker, M Bethge)
- A note on the evaluation of generative models (L Theis, A Oord, M Bethge)
- Approximating cnns with bag-of-local-features models works surprisingly well on imagenet (W Brendel, M Bethge)
- Controlling perceptual factors in neural style transfer (LA Gatys, AS Ecker, M Bethge, A Hertzmann, E Shechtman)
- Preserving color in neural artistic style transfer (LA Gatys, M Bethge, A Hertzmann, E Shechtman)
- Texture and art with deep neural networks (LA Gatys, AS Ecker, M Bethge)
- Generating spike trains with specified correlation coefficients (JH Macke, P Berens, AS Ecker, AS Tolias, M Bethge)
- Beyond GLMs: a generative mixture modeling approach to neural system identification (L Theis, AM Chagas, D Arnstein, C Schwarz, M Bethge)
- Towards causal generative scene models via competition of experts (J von Kügelgen, I Ustyuzhaninov, P Gehler, M Bethge, B Schölkopf)
- Diverse feature visualizations reveal invariances in early layers of deep neural networks (SA Cadena, MA Weis, LA Gatys, M Bethge, AS Ecker)
- Synthesising dynamic textures using convolutional neural networks (CM Funke, LA Gatys, AS Ecker, M Bethge)
- Texture synthesis using shallow convolutional networks with random filters (I Ustyuzhaninov, W Brendel, LA Gatys, M Bethge)
- Mixtures of conditional Gaussian scale mixtures applied to multiscale image representations (L Theis, R Hosseini, M Bethge)
- Modeling natural image statistics (HE Gerhard, L Theis, M Bethge)
- How Well do Feature Visualizations Support Causal Understanding of CNN Activations? (RS Zimmermann, J Borowski, R Geirhos, M Bethge, T Wallis, W Brendel)
- Exemplary natural images explain CNN activations better than feature visualizations (J Borowski, RS Zimmermann, J Schepers, R Geirhos, TSA Wallis, …)