# Learning from Web Data with Self-Organizing Memory Module

arXiv: https://arxiv.org/abs/1906.12028 · HTML: https://mlsanity.com/paper/1906.12028/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction](https://mlsanity.com/paper/2305.08740/) (2023)
- [Confidence-based Reliable Learning under Dual Noises](https://mlsanity.com/paper/2302.05098/) (2023)
- [GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence](https://mlsanity.com/paper/2307.09810/) (2023)
- [CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes](https://mlsanity.com/paper/2310.09761/) (2023)
- [FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning](https://mlsanity.com/paper/2212.00465/) (2022)
- [Deeply Dual Supervised learning for melanoma recognition](https://mlsanity.com/paper/2508.01994/) (2025)
- [Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling](https://mlsanity.com/paper/2508.06805/) (2025)
- [DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation](https://mlsanity.com/paper/2508.06816/) (2025)
- [VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagation](https://mlsanity.com/paper/2508.06819/) (2025)

## Abstract (arXiv)

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.