# Attend in groups: a weakly-supervised deep learning framework for learning from web data

arXiv: https://arxiv.org/abs/1611.09960 · HTML: https://mlsanity.com/paper/1611.09960/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2016.

## Built on by (most cited first, 12 of 12)

- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach](https://mlsanity.com/paper/2108.02399/) (2021)
- [From CNNs to Transformers in Multimodal Human Action Recognition: A Survey](https://mlsanity.com/paper/2405.15813/) (2024)
- [CycDA: Unsupervised Cycle Domain Adaptation from Image to Video](https://mlsanity.com/paper/2203.16244/) (2022)
- [Multi-Granularity Archaeological Dating of Chinese Bronze Dings Based on a Knowledge-Guided Relation Graph](https://mlsanity.com/paper/2303.15266/) (2023)
- [Improve Noise Tolerance of Robust Loss via Noise-Awareness](https://mlsanity.com/paper/2301.07306/) (2023)
- [Granular-ball Representation Learning for Deep CNN on Learning with Label Noise](https://mlsanity.com/paper/2409.03254/) (2024)
- [Self-Contained Entity Discovery from Captioned Videos](https://mlsanity.com/paper/2208.06662/) (2022)
- [Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones](https://mlsanity.com/paper/2101.09412/) (2021)
- [Few-shot Visual Relationship Co-localization](https://mlsanity.com/paper/2108.11618/) (2021)
- [Weak Novel Categories without Tears: A Survey on Weak-Shot Learning](https://mlsanity.com/paper/2110.02651/) (2021)
- [LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training](https://mlsanity.com/paper/2509.20786/) (2025)

## Abstract (arXiv)

Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to obtain, but direct training on such automatically harvested images can lead to unsatisfactory performance, because the noisy labels of Web images adversely affect the learned recognition models. To address this drawback we propose an end-to-end weakly-supervised deep learning framework which is robust to the label noise in Web images. The proposed framework relies on two unified strategies -- random grouping and attention -- to effectively reduce the negative impact of noisy web image annotations. Specifically, random grouping stacks multiple images into a single training instance and thus increases the labeling accuracy at the instance level. Attention, on the other hand, suppresses the noisy signals from both incorrectly labeled images and less discriminative image regions. By conducting intensive experiments on two challenging datasets, including a newly collected fine-grained dataset with Web images of different car models, the superior performance of the proposed methods over competitive baselines is clearly demonstrated.