Cross-Task Consistency Learning Framework for Multi-Task Learning

11/28/2021
by   Akihiro Nakano, et al.
0

Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features between tasks and enhance predictions compared to when learning each task independently. We propose a new learning framework for 2-task MTL problem that uses the predictions of one task as inputs to another network to predict the other task. We define two new loss terms inspired by cycle-consistency loss and contrastive learning, alignment loss and cross-task consistency loss. Both losses are designed to enforce the model to align the predictions of multiple tasks so that the model predicts consistently. We theoretically prove that both losses help the model learn more efficiently and that cross-task consistency loss is better in terms of alignment with the straight-forward predictions. Experimental results also show that our proposed model achieves significant performance on the benchmark Cityscapes and NYU dataset.

READ FULL TEXT

page 5

page 7

research
06/07/2020

Robust Learning Through Cross-Task Consistency

Visual perception entails solving a wide set of tasks, e.g., object dete...
research
11/22/2022

Mitigating Negative Transfer in Multi-Task Learning with Exponential Moving Average Loss Weighting Strategies

Multi-Task Learning (MTL) is a growing subject of interest in deep learn...
research
09/27/2021

Consistency Training of Multi-exit Architectures for Sensor Data

Deep neural networks have become larger over the years with increasing d...
research
05/17/2021

Deep Multistage Multi-Task Learning for Quality Prediction of Multistage Manufacturing Systems

In multistage manufacturing systems, modeling multiple quality indices b...
research
10/16/2019

Rugby-Bot: Utilizing Multi-Task Learning Fine-Grained Features for Rugby League Analysis

Sporting events are extremely complex and require a multitude of metrics...
research
09/19/2023

KFC: Kinship Verification with Fair Contrastive Loss and Multi-Task Learning

Kinship verification is an emerging task in computer vision with multipl...
research
03/10/2023

Adaptive Weight Assignment Scheme For Multi-task Learning

Deep learning based models are used regularly in every applications nowa...

Please sign up or login with your details

Forgot password? Click here to reset