Those two papers are about learning discrete representations from data by taking inspiration from vector quantization. Learning discrete representations using neural networks is challenging and can helpful for tasks such as compression, planning, reasoning, and can be potentially more interpretable than continuous ones. In the two papers use those learned discrete representations to build autoregressive generative models on image, sound, and video. The second paper (Generating Diverse High-Fidelity Images with VQ-VAE-2) is basically a sequel of the first (Neural Discrete Representation Learning) where they scale the models to bigger datasets and images (up to 1024x1024 resolution).
### Monday 30 March 10-11:30am - Full-Resolution Residual Networks for Semantic Segmentation
**Replacement date for canceled meeting at Monday 16 March 10-11:30am**
virtual meeting via dfnconf: https://conf.dfn.de/webapp/conference/97977564<br>
alternative link, if dfn is down: https://us04web.zoom.us/j/433015211
### Monday 30 March - Full-Resolution Residual Networks for Semantic Segmentation
Venue: **INM-1 Seminar room**, building 15.9, room 4001b
**Replacement date for canceled meeting at Monday 16 March**
* Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes (CVPR'17 Oral)<br>
T. Pohlen, A. Hermans, M. Mathias, and B. Leibe<br>
Most common architectures for semantic segmentation consisting of an encoder and decoder part (e.g. U-Net) heavily reduce the spatial dimension of input images and may loose important details or fail to localize precisely. The proposed papers present full-resolution networks, which try to preserve high-resolution features throughout the network and improve localization accuracy.
### Monday 17 February 10-11:30am - Speech Recognition
Venue: **INM-1 Seminar room**, building 15.9, room 4001b
### Monday 17 February - Speech Recognition
* Deep Speech 2: End-to-End Speech Recognition in English and Mandarin, Amodei et al., 2015<br>
https://arxiv.org/abs/1512.02595<br>
...
...
@@ -84,9 +125,7 @@ Speech Recognition with Deep Recurrent Neural Networks<br>
Alex Graves, Abdel-rahman Mohamed, Geoffrey Hinton, 2013<br>
https://arxiv.org/abs/1303.5778
### Monday 20 January 10-11:30am
Venue: **INM-1 Seminar room**, building 15.9, room 4001b
### Monday 20 January
* Multi-Context Recurrent Neural Networks for Time Series Applications <br>
Our first Journal Club will cover two papers from ICCV 2019 about GANs.
* SinGAN: Learning a Generative Model from a Single Natural Image (Best Paper Award) <br> http://openaccess.thecvf.com/content_ICCV_2019/papers/Shaham_SinGAN_Learning_a_Generative_Model_From_a_Single_Natural_Image_ICCV_2019_paper.pdf
