Reading_list

---

Unsupervised learning

Domain Generalization

Domain Adaptation

AAE

• AAE Makhzani, Alireza, et al. "Adversarial autoencoders." arXiv preprint arXiv:1511.05644 (2015).

GAN

pooling

• ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

Weakly Supervised Learning

• Weakly Supervised Object Localization with Progressive Domain Adaptation classification and detection 2 steps. only image labels. [CVPR 2016]
• [ICCV 2015 Deep Learning Face Attributes in the Wild ]
• CVPR 2017 Weakly Supervised Cascaded Convolutional Networks
• CVPR 2016 Large Scale Semi-supervised Object Detection using Visual and Semantic Knowledge Transfer
• [CVPR 2018 Class Peak Response](Class Peak Response)

Semi-supervised

• http://ruder.io/semi-supervised/

optic disk and optic cup segmentation

• Auto-Encoding Variational Bayes

segmentation

• a survey 2017 almost traditional methods Segmentation Techniques for Computer-Aided Diagnosis of Glaucoma: A Review ⭐⭐

• based on structural and gray level properties Segmentation of optic disk and optic cup from digital fundus images for the assessment of glaucoma no deep learning but very useful ideas. ⭐⭐⭐⭐

• convolutional filter + entropy sampling + convex hull transformation Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation too complicated ⭐⭐⭐

• semi-supervised Semi-supervised Segmentation of Optic Cup in Retinal Fundus Images Using Variational Autoencoder MICCAI 2017 ⭐⭐⭐⭐

• Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation 2018 TMI ⭐⭐⭐⭐⭐

• Deep Retinal Image Understanding 2016 MICCAI ⭐⭐⭐⭐⭐

domain adaptation

• Adversarial Discriminative Domain Adaptation CVPR 2017 ⭐⭐⭐⭐
• Adversarial Feature Augmentation for Unsupervised Domain Adaptation CVPR 2018. ⭐⭐⭐⭐⭐
• Unsupervised Pixel?Level Domain Adaptation with Generative Adversarial Networks CVPR 2017 ⭐⭐⭐⭐
• Boosting Domain Adaptation by Discovering Latent Domains CVPR 2018.oral
• Learning to Adapt Structured Output Space for Semantic Segmentation. CVPR 2018. GTA IoU: 42.4% SYNTHIA IoU: 46.7%
• Conditional Generative Adversarial Network for Structured Domain Adaptation CVPR 2018. GTA IoU 44.5%. SYNTHIA IoU: 41.2%
• Unsupervised Domain Adaptation with Similarity Learning for classification

[Domain Adaptation for Segmentation]

*CycleGAN Multimodal, shape constraints CVPR2018 ⭐⭐⭐⭐⭐

patch-level reinforesment learning

---

MIML (multi-instance multi label learning)

• Deep MIML Feng, Ji, and Zhi-Hua Zhou. "Deep MIML Network." AAAI. 2017.

MIL

• survey Carbonneau, Marc-André, et al. "Multiple instance learning: A survey of problem characteristics and applications." Pattern Recognition (2017).  another link here ⭐⭐⭐⭐⭐

Instance Space Method

• EM_DD Zhang, Qi, and Sally A. Goldman. "EM-DD: An improved multiple-instance learning technique." Advances in neural information processing systems. 2002. Implement ⭐⭐⭐⭐
• MI_SVM Andrews, Stuart, Ioannis Tsochantaridis, and Thomas Hofmann. "Support vector machines for multiple-instance learning." Advances in neural information processing systems. 2003. ⭐⭐⭐⭐
• MILBoost Zhang, Cha, John C. Platt, and Paul A. Viola. "Multiple instance boosting for object detection." Advances in neural information processing systems. 2006. ⭐⭐⭐⭐

Bag Space Method

• Diverse Density(DD) Maron, Oded, and Tomás Lozano-Pérez. "A framework for multiple-instance learning." Advances in neural information processing systems. 1998. Implement ⭐⭐⭐⭐

• citation kNN Wang, Jun, and Jean-Daniel Zucker. "Solving multiple-instance problem: A lazy learning approach." (2000): 1119-1125. Implement

• MInd Cheplygina, Veronika, David MJ Tax, and Marco Loog. "Multiple instance learning with bag dissimilarities." Pattern Recognition 48.1 (2015): 264-275.

• CCE Zhou, Zhi-Hua, and Min-Ling Zhang. "Solving multi-instance problems with classifier ensemble based on constructive clustering." Knowledge and Information Systems 11.2 (2007): 155-170. implement

• MILES Chen, Yixin, Jinbo Bi, and James Ze Wang. "MILES: Multiple-instance learning via embedded instance selection." IEEE Transactions on Pattern Analysis and Machine Intelligence 28.12 (2006): 1931-1947.

• NSK-SVM Gärtner, Thomas, et al. "Multi-instance kernels." ICML. Vol. 2. 2002.

• mi-Graph Zhou, Zhi-Hua, Yu-Yin Sun, and Yu-Feng Li. "Multi-instance learning by treating instances as non-iid samples." Proceedings of the 26th annual international conference on machine learning. ACM, 2009. implement

• BoW-SVM

• EMD-SVM Rubner, Yossi, Carlo Tomasi, and Leonidas J. Guibas. "The earth mover's distance as a metric for image retrieval." International journal of computer vision 40.2 (2000): 99-121.

Ranking

• **** Fast bundle algorithm for multiple-instance learning
• **** Multiple-instance ranking: Learning to rank images for image retrieval

others

• MIL pooling layer Kraus, Oren Z., Jimmy Lei Ba, and Brendan J. Frey. "Classifying and segmenting microscopy images with deep multiple instance learning." Bioinformatics 32.12 (2016): i52-i59.   ⭐⭐⭐⭐

• multi-instane neural network Ramon, Jan, and Luc De Raedt. "Multi instance neural networks." Proceedings of the ICML-2000 workshop on attribute-value and relational learning. 2000. ⭐⭐⭐

• ML-KNN Zhang, Min-Ling, and Zhi-Hua Zhou. "ML-KNN: A lazy learning approach to multi-label learning." Pattern recognition 40.7 (2007): 2038-2048.

MIL in Deep Learning

• Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition Yan, Zhennan, et al. "Multi-instance deep learning: Discover discriminative local anatomies for bodypart recognition." IEEE transactions on medical imaging 35.5 (2016): 1332-1343.
• MILCNN Sun, Miao, et al. "Multiple instance learning convolutional neural networks for object recognition." Pattern Recognition (ICPR), 2016 23rd International Conference on. IEEE, 2016.
• Attention Deep MIL Ilse, Maximilian, Jakub M. Tomczak, and Max Welling. "Attention-based Deep Multiple Instance Learning." arXiv preprint arXiv:1802.04712 (2018). ⭐⭐⭐⭐⭐⭐
• MINN Wang, Xinggang, et al. "Revisiting multiple instance neural networks." Pattern Recognition 74 (2018): 15-24. ⭐⭐⭐⭐⭐

SEMI-SUPERVISED LEARNING

• unsupervised loss function Sajjadi, Mehdi, Mehran Javanmardi, and Tolga Tasdizen. "Regularization with stochastic transformations and perturbations for deep semi-supervised learning." Advances in Neural Information Processing Systems. 2016.
• self-ensembling Laine, Samuli, and Timo Aila. "Temporal ensembling for semi-supervised learning." arXiv preprint arXiv:1610.02242 (2016).

Loss Function

• loss function based on probability map Jetley, Saumya, Naila Murray, and Eleonora Vig. "End-to-end saliency mapping via probability distribution prediction." Proceedings of Computer Vision and Pattern Recognition 2016 (2016): 5753-5761.
• L-GM loss for image classification Wan, Weitao, et al. "Rethinking Feature Distribution for Loss Functions in Image Classification." arXiv preprint arXiv:1803.02988 (2018). CVPR 2018 ⭐⭐⭐⭐⭐ implement
• Crystal Loss(softmax+l_2 norm) Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition. submitted to TPAMI 2018. previous version
• ring loss for face recognation Zheng, Yutong, Dipan K. Pal, and Marios Savvides. "Ring loss: Convex Feature Normalization for Face Recognition." arXiv preprint arXiv:1803.00130 (2018). CVPR 2018 ⭐⭐⭐⭐⭐ implement
• center loss Wen, Yandong, et al. "A discriminative feature learning approach for deep face recognition." European Conference on Computer Vision. Springer, Cham, 2016. ⭐⭐⭐⭐⭐

Feature Extraction

• Adaptive forward-backward greedy algorithm Zhang, Tong. "Adaptive forward-backward greedy algorithm for learning sparse representations." IEEE transactions on information theory 57.7 (2011): 4689-4708.