ReadingGroup

Getting involved

There is now a mailing list for this reading group. Send me (Damien) an email to get on it. No problem.

Note: this reading group is about deep learning as applied to depth estimation from a single image - one of the super hot topics. If your interest is deep learning in general, you may find some of the readings a little bit off-topic. So let me know if you want some idea about which you should read for.

Proposed Schedule

The below schedule is only proposed, and subject to change.

• 14 Sept 8.30am: Foley & Maitlin Chapter 6: Distance & Size Perception
• 21 Sept 8.30am: Saxena, Min & Ng: Make3D
• 28 Sept 8.30am: Michels, Saxena & Ng: High speed obstacle avoidance
• 05 Octr 8.30am: Karsch, Liu & Kang: Depth Transfer
• 12 Octr 8.30am: LeCun, Bengio & Hinton: Deep Learning Review
• 19 Octr 8.30am: LeCun, Bottou, Bengio & Haffner: CNNs
• 26 Octr 8.30am: Simonyan & Zisserman: VGG-16
• Week of 02 Novr: Break
• 09 Novr 8.30am: Eigen, Puhrsch & Fergus: Depth map prediction
• 16 Novr 8.30am: Shelhamer, Long & Darrell: Fully Convolutional Segmentation
• 23 Novr 8.30am: He, Zhang, Ren & Sun: ResNet
• 30 Novr 8.30am: Girshick, Donahue, Darrell & Malik: R-CNN
• 07 Decr 8.30am: Liao, Huang, Wang, Kodagoda, Yu & Liu: Fuse with laser
• 14 Decr 8.30am: Giuisti et al.: Forest trails CNN
• Week of 21 Decr: Break
• Week of 25 Decr: Cao, Wu & Shen: Fully convolutional depth 1
• Week of 01 Jany: Laina et al.: Fully convolutional depth 2
• Week of 08 Jany: Li, Klein & Yao: Fully convolutional depth 3
• Week of 15 Jany: Luo et al.: Deep Learning + Stereo
• Week of 22 Jany: Break
• Week of 29 Jany: Break
• Week of 06 Febr: Goodfellow et al.: Generative Adversarial Nets
• Week of 13 Febr: Dosovitskiy, Springenberg, Tatarchenko & Brox: Generating images
• Week of 20 Febr: Oord et al.: Pixel-RNN and Pixel-CNN
• Week of 27 Febr: Isola et al. Pix2Pix

Details

Foley & Maitlin Chapter 6 - Distance & Size Perception

https://books.google.com.tr/books?id=jLBmCgAAQBAJ&printsec=frontcover

Go to Chapter 6.

If that doesn't work (some have reported finding it difficult to access Chapter 6), try the following link: http://tinyurl.com/yalnnwp9 - some have reported being able to access the chapter by doing a google search for content.

Another thing to try that has worked for some is to log out of any google/gmail account before trying to access.

If nothing else works, email me.

Because our project is about using machine learning to extract depth from a single image (with deep learning, then applying it to robot problems) it pays to learn a bit about how humans do it.

Saxena, Min & Ng: Make3D

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4531745

This is the classic paper that brought machine learning to the problem of depth from a single image, quite successfully, considering previous attempts. It uses Markov Random Fields, which are a bit advanced but, importantly, quite slow.

Michels, Saxena & Ng: High speed obstacle avoidance

http://dl.acm.org/citation.cfm?id=1102426

Here the same authors focus on a related problem, that of determining open spaces for guiding a vehicle, again using machine learning techniques.

Karsch, Liu & Kang: Depth Transfer

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5551153

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6787109

This is a nonparametric approach to depth from a single image. They search a database of images similar to the observed one then warp the image retrieved from the database to estimate the depth of the current image.

LeCun, Bengio & Hinton: Deep Learning Review

http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html?foxtrotcallback=true

A whirlwind compressed intro to deep learning and its parts.

LeCun, Bottou, Bengio & Haffner: CNNs

http://ieeexplore.ieee.org/abstract/document/726791/

Here is the classic paper applying convolutional neural networks to image processing.

Krizhevsky, Sutskever & Hinton: ImageNet/AlexNet

https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

Here is when convolutional neural networks and deep learning really showed what it could do - the problem of image recognition.

But we won't use this because a lot of the complexity it introduces turns out not to be necessary. Later methods are "cleaner".

Simonyan & Zisserman: VGG-16

http://arxiv.org/abs/1409.1556

A relatively recent "deep" deep net with 16 layers for image recognition. Note: successful recent networks have one thousand layers.

Eigen, Puhrsch & Fergus: Depth map prediction

https://www.cs.nyu.edu/~deigen/depth/

Finally, we apply deep neural convolutional networks to the problem that we are interested in.

Shelhamer, Long & Darrell: Fully Convolutional Segmentation

http://arxiv.org/abs/1605.06211

Here a related problem is solved, that of semantic segmentation, but this approach is applicable to our problem.

Loffe & Szegedy: Batch Normalization

https://arxiv.org/abs/1502.03167

A recent technique that has enabled powerful new methods and ultimately much deeper neural networks. Important stuff.

He, Zhang, Ren & Sun: ResNets

https://arxiv.org/abs/1512.03385

This work and variations on it have been the basis of the 1000 layer recent neural networks. Important stuff.

Girshick, Donahue, Darrell & Malik: R-CNN

https://arxiv.org/abs/1311.2524

We take a slight seque to check out how tracking has been done recently with neural networks. Note that Faster-RCNN and more recent alternatives use similar principles but do it faster.

Liao, Huang, Wang, Kodagoda, Yu & Liu: Fuse with laser

https://arxiv.org/abs/1611.02174

Here we see an interesting depth-from-single-image sensor fusion with robotics applications.

Giuisti et al.: Forest trails CNN

http://ieeexplore.ieee.org/document/7358076/

See also youtube.

Here we have a CNN-based update to the learn-to-navigate-from-images problem addressed by Saxena et al. above.

Cao, Wu & Shen: Fully convolutional depth 1

http://arxiv.org/abs/1605.02305

Here we start a series of recent papers that take different approaches using deep nets to depth from a single image.

Laina et al.: Fully convolutional depth 2

http://arxiv.org/abs/1606.00373

Here we continue a series of recent papers that take different approaches using deep nets to depth from a single image.

Li, Klein & Yao: Fully convolutional depth 3

http://arxiv.org/abs/1607.00730

Here we finalise a series of recent papers that take different approaches using deep nets to depth from a single image.

Luo et al.: Deep Learning + Stereo

Combining deep learning and stereo.

https://www.cs.toronto.edu/~urtasun/publications/luo_etal_cvpr16.pdf

Goodfellow et al.: Generative Adversarial Nets

https://papers.nips.cc/paper/5423-generative-adversarial-nets

Another important recent development that we may make use of.

Dosovitskiy, Springenberg, Tatarchenko & Brox: Generating images

https://arxiv.org/abs/1411.5928

A non-adversarial approach to the same problem.

Oord et al.: Pixel-RNN & Pixel-CNN

https://arxiv.org/abs/1601.06759

Producing distributions over images. We have always intended to do something like this for depth images.

http://arxiv.org/abs/1606.05328

Isola et al. Pix2Pix

https://arxiv.org/abs/1611.07004

We can use this too. And it's cool.

List of interested people

(who I will contact with information about the schedule etc.)

• Abdulmajeed M. K.
• Alican M.
• Anas M.
• K. Bulut Ö.
• Imaduddin A. M.
• Tolga C.
• Bilge A.
• Hatice K.
• Hossein P.
• Torkan G.
• Buse Sibel K.
• Oğuzhan C.
• M. Alperen Ö.
• Hatice K.
• Özgür Ö.
• Doğay K.
• Onur A.
• Alper K.
• Furkan A.
• Elena B. S.
• Müjde A.
• Emeç E.

Additional Resources

EBook: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/DeepLearning-NowPublishing-Vol7-SIG-039.pdf Deep Learning: Methods and Applications by Li Deng and Dong Yu