Scalable Multitask Representation Learning for Scene Classification

By Maksim Lapin, Bernt Schiele, Matthias Hein. 2014

57 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Qiang Yang
3. Bernt Schiele
4. Abhinav Kumar Gupta
5. Qi Tian
6. Trevor Darrell
7. Yu Zhang
8. Luc Van Gool

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yi Yang
3. Qi Tian
4. Luc Van Gool
5. Xiaogang Wang
6. Bernt Schiele
7. Alan L. Yuille
8. Ming-Hsuan Yang

In Media Technology

1. Qi Tian
2. Jingdong Wang
3. Qiang Yang
4. Yu Zhang
5. Bernt Schiele
6. Abhinav Shrivastava
7. Martial Hebert
8. Lingxi Xie

Citations in the corpus

• An Overview of Multi-task Learning (2018, neutral): “Applications of MTL based on non-facial images include object categorization [86], image segmentation [89,90], identifying brain imaging predictors [91], saliency detection [92], action recognition [93], scene classification [94], multi-attribute prediction [95], multi-camera person re-identificatio”
• Cross-Stitch Networks for Multi-task Learning (2016, background): “However, most of such work, with publicly available code, formulates multi-task learning in an optimization framework that requires all data points in memory [6, 14, 23, 34, 49, 60, 61].”
• A Survey on Multi-Task Learning (2017, methodology): “In [157], a multi-task model is proposed to learn a low-dimensional feature transformation for scene classification.”
• On Better Exploring and Exploiting Task Relationships in Multitask Learning: Joint Model and Feature Learning (2018, methodology): “To improve the efficiency of multi-task learning on high-dimensional problems, a novel multi-task learning method was proposed by learning low-dimensional features of tasks jointly [13].”
• Multi-Task Learning with Low Rank Attribute Embedding for Person Re-Identification (2015, methodology): “It has been widely applied to machine learning [2, 44] and computer vision [45, 24].”
• Towards Reversal-Invariant Image Representation (2017, methodology): “The final vectors are square-root normalized followed by 2 normalized (Lapin et al. 2014), and then fed into LibLINEAR (Fan et al.”
• Efficient Output Kernel Learning for Multiple Tasks (2015, methodology): “In these experiments, we also compare our results with MTL-SDCA, a state-of-the-art multi-task feature learning method [25].”
• Top-k Multiclass SVM (2015, unknown): “0 LSH [16] 49.”
• Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, background): “Because of its promising performance in uncovering latent relationships among tasks, MTL has been widely used in machine learning [1], [2] and computer vision [3], [4] tasks.”