Multi What?

Multi-label Learning

CNN: Single-label to Multi-label

• paper: http://arxiv.org/abs/1406.5726

Deep Learning for Multi-label Classification

• paper: http://arxiv.org/abs/1502.05988
• code: http://meka.sourceforge.net

Predicting Unseen Labels using Label Hierarchies in Large-Scale Multi-label Learning(ECML2015)

• paper: https://www.kdsl.tu-darmstadt.de/fileadmin/user_upload/Group_KDSL/PUnL_ECML2015_camera_ready.pdf

Learning with a Wasserstein Loss

• arXiv: http://arxiv.org/abs/1506.05439
• project page: http://cbcl.mit.edu/wasserstein/
• code: http://cbcl.mit.edu/wasserstein/yfcc100m_labels.tar.gz
• MIT news: http://news.mit.edu/2015/more-flexible-machine-learning-1001

From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

• arxiv: http://arxiv.org/abs/1602.02068
• github: https://github.com/gokceneraslan/SparseMax.torch

Multi-task Learning

http://www.cs.cornell.edu/~kilian/research/multitasklearning/multitasklearning.html

multi-task learning

• discussion: https://github.com/memect/hao/issues/93

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

• intro: training a convolutional network to simultaneously classify, locate and detect objects in images can boost the classification accuracy and the detection and localization accuracy of all tasks
• arXiv: http://arxiv.org/abs/1312.6229
• code: https://github.com/sermanet/OverFeat
• code: http://cilvr.nyu.edu/doku.php?id=software:overfeat:start

Learning and Transferring Multi-task Deep Representation for Face Alignment

• arxiv: http://arxiv.org/abs/1408.3967

Multi-task learning of facial landmarks and expression

• paper: http://www.uoguelph.ca/~gwtaylor/publications/gwtaylor_crv2014.pdf

Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network

• paper: http://120.52.73.9/www.cv-foundation.org/openaccess/content_cvpr_workshops_2014/W15/papers/LI_Heterogeneous_Multi-task_Learning_2014_CVPR_paper.pdf

Deep Joint Task Learning for Generic Object Extraction(NIPS2014)

• homepage: http://vision.sysu.edu.cn/projects/deep-joint-task-learning/
• paper: http://ss.sysu.edu.cn/~ll/files/NIPS2014_JointTask.pdf
• github: https://github.com/xiaolonw/nips14_loc_seg_testonly
• dataset: http://objectextraction.github.io/

Learning deep representation of multityped objects and tasks

• arxiv: http://arxiv.org/abs/1603.01359

Multi-modal Learning

Multimodal Deep Learning

• paper: http://ai.stanford.edu/~ang/papers/nipsdlufl10-MultimodalDeepLearning.pdf

Multimodal Convolutional Neural Networks for Matching Image and Sentence

• homepage: http://mcnn.noahlab.com.hk/project.html
• paper: http://mcnn.noahlab.com.hk/ICCV2015.pdf
• arXiv: http://arxiv.org/abs/1504.06063