# Exploiting Web Images for Weakly Supervised Object Detection

arXiv: https://arxiv.org/abs/1707.08721 · HTML: https://mlsanity.com/paper/1707.08721/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2017.

## Built on by (most cited first, 5 of 5)

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2309.01331/) (2023)
- [Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection](https://mlsanity.com/paper/2108.13775/) (2021)
- [PanorAMS: Automatic Annotation for Detecting Objects in Urban Context](https://mlsanity.com/paper/2208.14295/) (2022)
- [Development of Image Collection Method Using YOLO and Siamese Network](https://mlsanity.com/paper/2410.12561/) (2024)

## Abstract (arXiv)

In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations that require extensive human labelling. Object detection without bounding box annotations, i.e, weakly supervised detection methods, are still lagging far behind. As weakly supervised detection only uses image level labels and does not require the ground truth of bounding box location and label of each object in an image, it is generally very difficult to distill knowledge of the actual appearances of objects. Inspired by curriculum learning, this paper proposes an easy-to-hard knowledge transfer scheme that incorporates easy web images to provide prior knowledge of object appearance as a good starting point. While exploiting large-scale free web imagery, we introduce a sophisticated labour free method to construct a web dataset with good diversity in object appearance. After that, semantic relevance and distribution relevance are introduced and utilized in the proposed curriculum training scheme. Our end-to-end learning with the constructed web data achieves remarkable improvement across most object classes especially for the classes that are often considered hard in other works.