Papers › Learning from Web Data with Self-Organizing Memory Module

Learning from Web Data with Self-Organizing Memory Module

28 Jun 2019CVPR 2020 6arXiv:1906.12028archive 2025-07-28

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification WebVision-1000 SOMNet (ResNet-50) ImageNet Top-1 Accuracy 65.0% #14 of 16 Archive leaderboard report
Image Classification WebVision-1000 SOMNet (ResNet-50) ImageNet Top-5 Accuracy 85.1% #14 of 16 Archive leaderboard report
Image Classification WebVision-1000 SOMNet (ResNet-50) Top-1 Accuracy 72.2% #14 of 16 Archive leaderboard report
Image Classification WebVision-1000 SOMNet (ResNet-50) Top-5 Accuracy 89.5% #14 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections