Deep Metric Transfer for Label Propagation with Limited Annotated Data

12/20/2018
by   Bin Liu, et al.
12

We study object recognition under the constraint that each object class is only represented by very few observations. In such cases, naive supervised learning would lead to severe over-fitting in deep neural networks due to limited training data. We tackle this problem by creating much more training data through label propagation from the few labeled examples to a vast collection of unannotated images. Our main insight is that such a label propagation scheme can be highly effective when the similarity metric used for propagation is learned and transferred from other related domains with lots of data. We test our approach on semi-supervised learning, transfer learning and few-shot recognition, where we learn our similarity metric using various supervised/unsupervised pretraining methods, and transfer it to unlabeled data across different data distributions. By taking advantage of unlabeled data in this way, we achieve significant improvements on all three tasks. Notably, our approach outperforms current state-of-the-art techniques by an absolute 20% for semi-supervised learning on CIFAR10, 10% for transfer learning from ImageNet to CIFAR10, and 6% for few-shot recognition on mini-ImageNet, when labeled examples are limited.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 9

research
09/02/2021

Transfer of Pretrained Model Weights Substantially Improves Semi-Supervised Image Classification

Deep neural networks produce state-of-the-art results when trained on a ...
research
03/25/2022

Digital Fingerprinting of Microstructures

Finding efficient means of fingerprinting microstructural information is...
research
08/25/2020

Learning to Learn in a Semi-Supervised Fashion

To address semi-supervised learning from both labeled and unlabeled data...
research
03/09/2020

Embedding Propagation: Smoother Manifold for Few-Shot Classification

Few-shot classification is challenging because the data distribution of ...
research
03/15/2018

Deep Co-Training for Semi-Supervised Image Recognition

In this paper, we study the problem of semi-supervised image recognition...
research
10/01/2020

Using ROC and Unlabeled Data for Increasing Low-Shot Transfer Learning Classification Accuracy

One of the most important characteristics of human visual intelligence i...
research
08/13/2021

Progressive Representative Labeling for Deep Semi-Supervised Learning

Deep semi-supervised learning (SSL) has experienced significant attentio...

Please sign up or login with your details

Forgot password? Click here to reset