# Deep Learning Logo Detection with Data Expansion by Synthesising Context

arXiv: https://arxiv.org/abs/1612.09322 · HTML: https://mlsanity.com/paper/1612.09322/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2016.

## Built on by (most cited first, 13 of 13)

- [VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios](https://mlsanity.com/paper/2101.01394/) (2021)
- [FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network](https://mlsanity.com/paper/2108.04644/) (2021)
- [Deep Learning for Logo Detection: A Survey](https://mlsanity.com/paper/2210.04399/) (2022)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps](https://mlsanity.com/paper/2108.09104/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Reconstruction guided Meta-learning for Few Shot Open Set Recognition](https://mlsanity.com/paper/2108.00340/) (2021)
- [FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings](https://mlsanity.com/paper/2308.09012/) (2023)
- [VersatileGait: A Large-Scale Synthetic Gait Dataset Towards in-the-Wild Simulation](https://mlsanity.com/paper/2105.14421/) (2021)
- [Detecting and Segmenting Adversarial Graphics Patterns from Images](https://mlsanity.com/paper/2108.09383/) (2021)
- [Automatic travel pattern extraction from visa page stamps using CNN models](https://mlsanity.com/paper/2112.00348/) (2021)
- [Rooms with Text: A Dataset for Overlaying Text Detection](https://mlsanity.com/paper/2211.11350/) (2022)
- [Contrastive Multi-View Textual-Visual Encoding: Towards One Hundred Thousand-Scale One-Shot Logo Identification](https://mlsanity.com/paper/2211.12926/) (2022)

## Abstract (arXiv)

Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of improving significantly logo detection performance when only a handful of (e.g., 10) labelled training images captured in realistic context are available, avoiding extensive manual labelling costs. Specifically, we design a novel algorithm for generating Synthetic Context Logo (SCL) training images to increase model robustness against unknown background clutters, resulting in superior logo detection performance. For benchmarking model performance, we introduce a new logo detection dataset TopLogo-10 collected from top 10 most popular clothing/wearable brandname logos captured in rich visual context. Extensive comparisons show the advantages of our proposed SCL model over the state-of-the-art alternatives for logo detection using two real-world logo benchmark datasets: FlickrLogo-32 and our new TopLogo-10.