by Zhiming Luo
Girshick et al. “Rich feature hierarchies for accurate object detection and semantic segmentation.” CVPR. 2014.
He et al. “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition.” TPAMI. 2015.
- Fast RCNN, OHEM
Girshick. “Fast R-CNN.” ICCV. 2015.
Shrivastava et al. “Training Region-based Object Detectors with Online Hard Example Mining.” CVPR. 2016.
- Faster RCNN:
Ren et al. “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” NIPS. 2015.
Zhang et al. “Is Faster R-CNN Doing Well for Pedestrian Detection.” ECCV. 2016.
- YOLO, SSD
Redmon et al. “You Only Look Once: Unified, Real-Time Object Detection.” CVPR. 2016.
Liu et al. “SSD: Single Shot MultiBox Detector.” ECCV. 2016.
Reading group on Spectral Clustering (led by P-M Jodoin)
K-Means Spectral Clustering
Presentation is HERE
Reading group on superpixels (led by Yi Wang)
papers can be downloaded here : superpixel.tar.
Presentation by Yi Wang.
By Clement Zotti
- using sshkey
- sshfs (only available for linux user, for windows bitwise provide a sftp connection that enable file transfert throught ssh)
- screen & byubu
- grep & ack-grep
Introduction by Yi:
Since everyone is working with machine learning, the reading group for the next week would be about imbalanced learning.
Continue reading Imbalanced Learning
Introduction by Zhiming:
For the next week’s reading group, I propose that we have a topic about Ensemble Learning Methods, and there will be two slides for these reading group. Hoping through this reading group, everyone has a basic idea about ensemble learning and knows a new method called Gradient Boosting Trees.
Continue reading Ensemble Learning Methods
Introduction by Martin:
This Friday’s reading group will be a hands-on tutorial on multiprocessing in Python. Please make sure to have Python 2 installed on your laptop. No further preparation needed, if you want an IDE: Spyder is decent. Slides.
- CPU count
- Process class
- Pool class
- Hands-on challenge!
A different formula will be attempted for this reading group: everyone shall each study their own paper on the subject of Recurrent Neural Networks (RNN) or Long Short-Term Memory (LSTM), and present it.
List of the available papers
Reading group about Git by Clément.
- Starting a git repository
- Useful commands for current status of repository
- Working with branches to develop features
- Committing your work
- Reverting changes
- Merging back into master
- Merging problems
Reading group by Pierre-Marc on sparse coding.
L0 is the ultimate sparsity measure but L1 is also a good approximation for sparsity. Sparse coding is very good for compression, inpainting and denoising.