#1. Topic: Pooling Mechanism Date: 10-12-2018, 4:00-5:00 pm, C3.101 Lecturer: Zenglin Shi Slides: Papers:
- Faraz Saeedan, Nicolas Weber, Michael Goesele and Stefan Roth. Detail-Preserving Pooling in Deep Networks. CVPR, 2018 (Oral).
- Y-Lan BoureauA, Jean Ponce and Yann LeCun. Theoretical Analysis of Feature Pooling in Visual Recognition. ICML, 2010.
- ZenglinShi, YangdongYe and Yunpeng Wu. Rank-based pooling for deep convolutional neural networks. Neural Networks,2016.
#2. Topic: Transfer Learning Date: 10-12-2018, 4:00-5:00 pm, C3.101 Lecturer: Riaan Zoetmulder Slides: Papers:
- Amir R. Zamir, Alexander Sax, William Shen, Leonidas Guibas, Jitendra Malik and Silvio Savarese. Taskonomy: Disentangling Task Transfer Learning. CVPR, 2018 (Best Paper). [pdf]
#3 Topic: Model Pretraining Date: 17-12-2018, 4:00-5:00 pm, C3.101 Lecturer: William Thong Slides: Papers:
- Kaiming He, Ross Girshick and Piotr Dollar. Rethinking ImageNet Pre-training. Arxiv, 2018.
#4 Topic: Understanding Convolutions Date: 17-12-2018 and 07-01-2019 4:00-5:00 pm, C3.101 Lecturer: Tao Hu, Shuo Chen Slides: Papers:
- J. Dai et al. Deformable Convolutional Networks. ICCV, 2017.
- Xizhou Zhu, Han Hu, Stephen Lin and Jifeng Dai. Deformable ConvNets v2: More Deformable, Better Results2. Arxiv, 2018.
- Tianyi Wu et al. Tree-structured Kronecker Convolutional Network for Semantic Segmentation. Arxiv, 2018.
#5 Topic: Normalization Date: 07-01-2019, 4:00-5:00 pm, C3.101 Lecturer: Zenglin Shi Slides: Papers:
- Yuxin Wu, Kaiming He. Group Normalization. ECCV, 2018.
- Sergey Ioffe. Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models. NIPS, 2017
- Sergey Ioffe and Christian Szegedy. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. ICML, 2015.