A Modulation Module for Multi-task Learning with Applications in Image Retrieval

@inproceedings{Zhao2018AMM,
  title={A Modulation Module for Multi-task Learning with Applications in Image Retrieval},
  author={Xiangyu Zhao and Haoxiang Li and Xiaohui Shen and Xiaodan Liang and Ying Wu},
  booktitle={ECCV},
  year={2018}
}
Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each other. However, the relationships between the tasks are complicated in practice, especially when the number of involved tasks scales up. When two tasks are of weak relevance, they may compete or even distract each other during joint training of shared… 
Many Task Learning With Task Routing
TLDR
This paper introduces Many Task Learning (MaTL) as a special case of MTL where more than 20 tasks are performed by a single model and applies a conditional feature-wise transformation over the convolutional activations that enables a model to successfully perform a large number of tasks.
Regularizing Deep Multi-Task Networks using Orthogonal Gradients
TLDR
This work proposes a novel gradient regularization term that minimizes task interference by enforcing near orthogonal gradients and encourages task specific decoders to optimize different parts of the feature extractor, thus reducing competition.
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference
TLDR
The reparameterization enables the model to learn new tasks without adversely affecting the performance of existing ones and achieves state-of-the-art on two challenging multi-task learning benchmarks, PASCAL-Context and NYUD, and also demonstrates superior incremental learning capability as compared to its close competitors.
Multi-Task Learning with Deep Neural Networks: A Survey
TLDR
An overview of multi-task learning methods for deep neural networks is given, with the aim of summarizing both the well-established and most recent directions within the field.
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification
  • L. Liebel, M. Körner
  • Computer Science
    2019 IEEE Intelligent Transportation Systems Conference (ITSC)
  • 2019
TLDR
MultiDepth, a novel training strategy and convolutional neural network architecture that allows approaching single-image depth estimation (SIDE) as a multi-task problem, is introduced and it is shown that end-to-end multitask learning with both, regression and classification, is able to considerably improve training and yield more accurate results.
Revisiting Multi-Task Learning in the Deep Learning Era
TLDR
This survey provides a well-rounded view on state-of-the-art MTL techniques within the context of deep neural networks and examines various optimization methods to tackle the joint learning of multiple tasks.
Attentive Single-Tasking of Multiple Tasks
In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as
Deep Convolutional Neural Network with Multi-Task Learning Scheme for Modulations Recognition
TLDR
This paper proposes a multi-task learning (MTL) approach to recognize the modulation scheme used among a specific set of analog and digital modulations, which uses a deep convolutional neural network to extract the necessary features in order to classify the different modulation schemes.
Task Switching Network for Multi-task Learning
TLDR
This work demonstrates for the first time that multi-tasking can be performed with a single task-conditioned decoder, and achieves this by learning task-specific conditioning parameters through a jointly trained task embedding network, encouraging constructive interaction between tasks.
Adversarial Multi-task Label Embedding for Text Classification
TLDR
The Adversarial Multi-task Label Embedding model is proposed, which introduces adversarial training and orthogonal constraints into the multi-task learning framework to prevent shared features and private features from interacting with each other.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 38 REFERENCES
Fully-Adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification
TLDR
Evaluation on person attributes classification tasks involving facial and clothing attributes suggests that the models produced by the proposed method are fast, compact and can closely match or exceed the state-of-the-art accuracy from strong baselines by much more expensive models.
Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition
TLDR
A dynamic-weighting scheme to automatically assign the loss weights to each side task solves the crucial problem of balancing between different tasks in MTL and achieves comparable or better performance on LFW, CFP, and IJB-A datasets.
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
TLDR
This paper investigates a framework of deep learning with application to CBIR tasks with an extensive set of empirical studies by examining a state-of-the-art deep learning method (Convolutional Neural Networks) for CBIr tasks under varied settings.
Cross-Stitch Networks for Multi-task Learning
TLDR
This paper proposes a principled approach to learn shared representations in Convolutional Networks using multitask learning using a new sharing unit: "cross-stitch" unit that combines the activations from multiple networks and can be trained end-to-end.
Deep Cross Residual Learning for Multitask Visual Recognition
TLDR
It is shown how cross-residual learning (CRL) can be integrated in multitask networks to jointly train and detect visual concepts across several tasks to achieve competitive, or even better, detection performance on a visual sentiment concept detection problem normally requiring multiple specialized single-task networks.
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory
  • I. Kokkinos
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
In this work we train in an end-to-end manner a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture. Such a network can act like
HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition
TLDR
The proposed method, HyperFace, fuses the intermediate layers of a deep CNN using a separate CNN followed by a multi-task learning algorithm that operates on the fused features to exploit the synergy among the tasks which boosts up their individual performances.
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
TLDR
This work presents a new model for simultaneous depth estimation and semantic segmentation from a single RGB image and couple the deep CNN with fully connected CRF, which captures the contextual relationships and interactions between the semantic and depth cues improving the accuracy of the final results.
Densely Connected Convolutional Networks
TLDR
The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
...
1
2
3
4
...