Deep Cross Residual Learning for Multitask Visual Recognition

04/05/2016
by   Brendan Jou, et al.
0

Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integration of complex relations between closely coupled recognition tasks or across domains. Such problems are often encountered in multimedia applications involving large-scale content recognition. We propose a novel extension of residual learning for deep networks that enables intuitive learning across multiple related tasks using cross-connections called cross-residuals. These cross-residuals connections can be viewed as a form of in-network regularization and enables greater network generalization. We show how cross-residual learning (CRL) can be integrated in multitask networks to jointly train and detect visual concepts across several tasks. We present a single multitask cross-residual network with >40 parameters that is able to achieve competitive, or even better, detection performance on a visual sentiment concept detection problem normally requiring multiple specialized single-task networks. The resulting multitask cross-residual network also achieves better detection performance by about 10.4 even a small amount of cross-task weighting.

READ FULL TEXT

page 2

page 8

research
06/28/2016

Modeling Industrial ADMET Data with Multitask Networks

Deep learning methods such as multitask neural networks have recently be...
research
08/25/2023

Learning Compact Neural Networks with Deep Overparameterised Multitask Learning

Compact neural network offers many benefits for real-world applications....
research
08/11/2021

MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach

Multitask learning is a common approach in machine learning, which allow...
research
10/30/2019

Generalization in multitask deep neural classifiers: a statistical physics approach

A proper understanding of the striking generalization abilities of deep ...
research
11/07/2017

GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks

Deep multitask networks, in which one neural network produces multiple p...
research
06/05/2016

Multimodal Residual Learning for Visual QA

Deep neural networks continue to advance the state-of-the-art of image r...
research
05/28/2019

Deep Scale-spaces: Equivariance Over Scale

We introduce deep scale-spaces (DSS), a generalization of convolutional ...

Please sign up or login with your details

Forgot password? Click here to reset