Webly Supervised Learning of Convolutional Networks

05/07/2015
by   Xinlei Chen, et al.
0

We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN style detector. It achieves the best performance on VOC 2007 where no VOC training data is used. Finally, we show our approach is quite robust to noise and performs comparably even when we use image search results from March 2013 (pre-CNN image search era).

READ FULL TEXT

page 1

page 3

page 5

page 6

page 8

page 9

research
03/31/2018

Webly Supervised Learning for Skin Lesion Classification

Within medical imaging, manual curation of sufficient well-labeled sampl...
research
10/02/2016

Deep unsupervised learning through spatial contrasting

Convolutional networks have marked their place over the last few years a...
research
06/03/2015

One-to-many face recognition with bilinear CNNs

The recent explosive growth in convolutional neural network (CNN) resear...
research
08/03/2018

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

We present a simple yet efficient approach capable of training deep neur...
research
03/16/2021

Machine learning initialization to accelerate Stokes profile inversions

In this work, we discuss the application of convolutional neural network...
research
06/14/2017

Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition

Webly-supervised learning has recently emerged as an alternative paradig...
research
08/20/2021

Web image search engine based on LSH index and CNN Resnet50

To implement a good Content Based Image Retrieval (CBIR) system, it is e...

Please sign up or login with your details

Forgot password? Click here to reset