Reading Assignment: Advanced CNN Architectures

Main Reading

Note: This reading assignment spans 2 weeks. You can distribute the load as you like. But we highly recommend not to wait too long.

Start with the high-level overview provided in this blog post by Adit Deshpande. Anything beyond the section on region-based CNNs is optional. (GANs are covered in the “Learning Generative Models” course.)

Next, read Densely connected convolutional networks (2016), Huang et al. There is a lot to learn from this paper as the authors do a very good job pointing out similarities and differences with many related approaches.

Selective Reading (i.e. pick one!)

As additional (mandatory) reading assignment for the 2nd week, here are 6 papers that use (and extend) CNNs in various settings. They are all worth reading, but you just need to read one of them.

Please use the OVGU GitLab issue system to choose your paper by voting for the respective issue! Pick the one you are most interested in unless it already has 10 votes. In that case, consider reading a less popular one because we are aiming for a balanced distribution. Of course, you can also read more than one paper.

Here are some questions to guide you during reading:

• What is the learning problem? (datasets, representation of inputs and outputs, cost function and evaluation measures) Which specific challenges are addressed?
• What does the network design look like? (Try to understand the details as if you were to implement the described architecture!)
• What are the main innovations described in the paper? Where does it go beyond the techniques covered in the deep learning book?
• What are the main experimental findings?
• Does the paper have any weak spots?
• Is there any information on performance (throughput) and hardware requirements?

You should be prepared to explain the most important / innovative aspects of the paper to others.

1. A convolutional neural network for modeling sentences (2014), N. Kalchbrenner et al.

2. End-to-end Learning for Music Audio Tagging at Scale (2018), J. Pons et al.

3. Image style transfer using convolutional neural networks (2016), L.A. Gatys et al.

4. Image Super-Resolution Using Deep Convolutional Networks (2016), C. Dong et al.

5. Singing voice separation with deep U-Net convolutional networks (2017), A. Jansson et al.

6. You only look once: Unified, real-time object detection (2016), J. Redmon et al.

Optional Further Reading

If you would like to dig deeper, here are some more ressources:

• on ResNets: Deep residual learning for image recognition (2016), K. He et al.
• on Inception architectures: Rethinking the inception architecture for computer vision (2016), C. Szegedy et al.
• on 1x1 convolution: One by One [ 1 x 1 ] Convolution - counter-intuitively useful (2016), A. Prakash
• on convolution arithmatic A guide to convolution arithmetic for deep learning (2016), V. Dumoulin & F. Visin