Learning Multiple Tasks with Multilinear Relationship Networks

By Mingsheng Long, Zhangjie Cao, Jianmin Wang, Philip S. Yu. 2015

350 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks (2017, methodology): “We try two different models: (1) a SegNet (Badrinarayanan et al. (2015); Lee et al. (2017)) network with a symmetric VGG16 (Simonyan & Zisserman (2014)) encoder/decoder, and (2) an FCN (Long et al. (2015)) network with a modiﬁed ResNet-50 (He et al. (2016) learns all upsampling ﬁlters.”
Which Tasks Should Be Learned Together in Multi-task Learning? (2019, methodology): “Hard parameter sharing is also used in many other works such as [42, 4, 27, 12, 17, 2, 33, 10, 45, 19, 23, 8, 47, 36].”
Multi-Task Learning for Dense Prediction Tasks: A Survey (2020, methodology): “example, multilinear relationship networks [55] used tensor normal priors to the parameter set of the task-specific heads Backbone Sc al e 1/ 32 Distillation Scale 1/32”
A Decade Survey of Transfer Learning (2010–2020) (2020, unknown): “Furthermore, [50] presented Multilinear Relationship Networks(MRN).”
Zero-Shot Task Transfer (2019, background): “arns multiple tasks simultaneously with a view of task generalization. Some methods in multi-task learning assume a prior and then iterate to learn a joint space of tasks [7][19], while other methods [26][19] do not use a prior but learn a joint space of tasks during the process of learning. Distrib”
Adaptive Auxiliary Task Weighting for Reinforcement Learning (2019, background): “task relationships to be known as a prior [25], or learned from the relationships among task specific parameters [26, 27].”
Efficient Multitask Feature and Relationship Learning (2017, methodology): “As another baseline, we also compare our method with the multilin-ear relationship network (Long et al., 2017), which can be understood as an extension of the MTFRL method using neural networks ( MTFRL-NN ).”
Visual Reasoning by Progressive Module Networks (2018, methodology): “The process of training a machine learning model to be able to solve multiple tasks, or multi-task learning (MTL), has been widely studied (Long et al., 2017; Ruder, 2017; Ruder et al., 2017; Rusu et al., 2016).”
Gradient Adversarial Training of Neural Networks (2018, background): “In multi-task learning, a single network is trained end-to-end to achieve multiple related but different task outputs for an input [19].”
Geometry Uncertainty Projection Network for Monocular 3D Object Detection (2021, background): “Many works focus on task relation representation learning [28, 45, 48, 51, 52, 53].”