Improving task-specific representation via 1M unlabelled images without any extra knowledge

We present a case-study to improve the task-specific representation by leveraging a million unlabelled images without any extra knowledge. We propose an exceedingly simple method of conditioning an existing representation on a diverse data distribution and observe that a model trained on diverse exa...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-06
Main Author: Bansal, Aayush
Format: Article
Language:English
Subjects:
Computer architecture
Image segmentation
Neural networks
Parameter modification
Representations
Semantic segmentation
Semantics
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a case-study to improve the task-specific representation by leveraging a million unlabelled images without any extra knowledge. We propose an exceedingly simple method of conditioning an existing representation on a diverse data distribution and observe that a model trained on diverse examples acts as a better initialization. We extensively study our findings for the task of surface normal estimation and semantic segmentation from a single image. We improve surface normal estimation on NYU-v2 depth dataset and semantic segmentation on PASCAL VOC by 4% over base model. We did not use any task-specific knowledge or auxiliary tasks, neither changed hyper-parameters nor made any modification in the underlying neural network architecture.
ISSN:2331-8422