Improving Self-supervised Learning for Out-of-distribution Task via Auxiliary Classifier

09/07/2022
by   Harshita Boonlia, et al.
0

In real world scenarios, out-of-distribution (OOD) datasets may have a large distributional shift from training datasets. This phenomena generally occurs when a trained classifier is deployed on varying dynamic environments, which causes a significant drop in performance. To tackle this issue, we are proposing an end-to-end deep multi-task network in this work. Observing a strong relationship between rotation prediction (self-supervised) accuracy and semantic classification accuracy on OOD tasks, we introduce an additional auxiliary classification head in our multi-task network along with semantic classification and rotation prediction head. To observe the influence of this addition classifier in improving the rotation prediction head, our proposed learning method is framed into bi-level optimisation problem where the upper-level is trained to update the parameters for semantic classification and rotation prediction head. In the lower-level optimisation, only the auxiliary classification head is updated through semantic classification head by fixing the parameters of the semantic classification head. The proposed method has been validated through three unseen OOD datasets where it exhibits a clear improvement in semantic classification accuracy than other two baseline methods. Our code is available on GitHub <https://github.com/harshita-555/OSSL>

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/10/2021

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?

Understanding classifier decision under novel environments is central to...
research
01/24/2021

Improving Few-Shot Learning with Auxiliary Self-Supervised Pretext Tasks

Recent work on few-shot learning <cit.> showed that quality of learned r...
research
01/25/2019

Self-Supervised Generalisation with Meta Auxiliary Learning

Learning with auxiliary tasks has been shown to improve the generalisati...
research
03/14/2022

MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks

In many personalized recommendation scenarios, the generalization abilit...
research
01/29/2022

FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss

The existence of completely aligned and paired multi-modal neuroimaging ...
research
08/27/2022

Multi-Outputs Is All You Need For Deblur

Image deblurring task is an ill-posed one, where exists infinite feasibl...
research
07/20/2022

Tailoring Self-Supervision for Supervised Learning

Recently, it is shown that deploying a proper self-supervision is a pros...

Please sign up or login with your details

Forgot password? Click here to reset