Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification

by   Jia Li, et al.

Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is overwhelmed by noisy images with inadequate and inaccurate tags. In this paper, we propose a Ubiquitous Reweighting Network (URNet) that learns an image classification model from large-scale noisy data. By observing the web data, we find that there are five key challenges, , imbalanced class sizes, high intra-classes diversity and inter-class similarity, imprecise instances, insufficient representative instances, and ambiguous class labels. To alleviate these challenges, we assume that every training instance has the potential to contribute positively by alleviating the data bias and noise via reweighting the influence of each instance according to different class sizes, large instance clusters, its confidence, small instance bags and the labels. In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet. Experimental results in the WebVision 2018 challenge with 16 million noisy training images from 5000 classes show that our approach outperforms state-of-the-art models and ranks the first place in the image classification task.


page 3

page 5

page 6

page 8


Noisy Label Learning for Large-scale Medical Image Classification

The classification accuracy of deep learning models depends not only on ...

Combating Noisy Labels in Long-Tailed Image Classification

Most existing methods that cope with noisy labels usually assume that th...

Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data

Jointly extracting entity pairs and their relations is challenging when ...

CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise

In this paper, we study the problem of learning image classification mod...

Weakly Supervised Learning with Side Information for Noisy Labeled Images

In many real-world datasets, like WebVision, the performance of DNN base...

2nd Place Solution for ICCV 2021 VIPriors Image Classification Challenge: An Attract-and-Repulse Learning Approach

Convolutional neural networks (CNNs) have achieved significant success i...

Learning Subclass Representations for Visually-varied Image Classification

In this paper, we present a subclass-representation approach that predic...

Please sign up or login with your details

Forgot password? Click here to reset