Learning from Web Data with Self-Organizing Memory Module

CVPR 2020  ·  Yi Tu, Li Niu, Junjie Chen, Dawei Cheng, Liqing Zhang ·

Learning from web data has attracted lots of research interest in recent years. However, crawled web images usually have two types of noises, label noise and background noise, which induce extra difficulties in utilizing them effectively. Most existing methods either rely on human supervision or ignore the background noise. In this paper, we propose a novel method, which is capable of handling these two types of noises together, without the supervision of clean images in the training stage. Particularly, we formulate our method under the framework of multi-instance learning by grouping ROIs (i.e., images and their region proposals) from the same category into bags. ROIs in each bag are assigned with different weights based on the representative/discriminative scores of their nearest clusters, in which the clusters and their scores are obtained via our designed memory module. Our memory module could be naturally integrated with the classification module, leading to an end-to-end trainable system. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our method.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract
No code implementations yet. Submit your code now
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification WebVision-1000 SOMNet (ResNet-50) Top-1 Accuracy 72.2% # 14
Top-5 Accuracy 89.5% # 11
ImageNet Top-1 Accuracy 65.0% # 8
ImageNet Top-5 Accuracy 85.1% # 8

Methods


No methods listed for this paper. Add relevant methods here