Data Distillation: Towards Omni-Supervised Learning

12/12/2017
by   Ilija Radosavovic, et al.
0

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lower-bounded by performance on existing labeled datasets, offering the potential to surpass state-of-the-art fully supervised methods. To exploit the omni-supervised setting, we propose data distillation, a method that ensembles predictions from multiple transformations of unlabeled data, using a single model, to automatically generate new training annotations. We argue that visual recognition models have recently become accurate enough that it is now possible to apply classic ideas about self-training to challenging real-world data. Our experimental results show that in the cases of human keypoint detection and general object detection, state-of-the-art models trained with data distillation surpass the performance of using labeled data from the COCO dataset alone.

READ FULL TEXT

page 4

page 5

page 8

research
06/03/2020

Interpolation-based semi-supervised learning for object detection

Despite the data labeling cost for the object detection tasks being subs...
research
09/05/2019

FraudJudger: Real-World Data Oriented Fraud Detection on Digital Payment Platforms

Automated fraud behaviors detection on electronic payment platforms is a...
research
11/04/2021

Building Damage Mapping with Self-PositiveUnlabeled Learning

Humanitarian organizations must have fast and reliable data to respond t...
research
08/08/2023

Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation

Adversarial robustness is a research area that has recently received a l...
research
01/15/2020

Proposal Learning for Semi-Supervised Object Detection

In this paper, we focus on semi-supervised object detection to boost acc...
research
05/30/2017

Semi-Supervised Learning for Detecting Human Trafficking

Human trafficking is one of the most atrocious crimes and among the chal...
research
12/15/2021

Taming Overconfident Prediction on Unlabeled Data from Hindsight

Minimizing prediction uncertainty on unlabeled data is a key factor to a...

Please sign up or login with your details

Forgot password? Click here to reset