# Large Scale Open-Set Deep Logo Detection

arXiv: https://arxiv.org/abs/1911.07440 · HTML: https://mlsanity.com/paper/1911.07440/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2019.

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

- [Image-Text Pre-Training for Logo Recognition](https://mlsanity.com/paper/2309.10206/) (2023)
- [AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status](https://mlsanity.com/paper/2409.17740/) (2024)
- [Makeup216: Logo Recognition with Adversarial Attention Representations](https://mlsanity.com/paper/2112.06533/) (2021)
- [Detecting Cloud-Based Phishing Attacks by Combining Deep Learning Models](https://mlsanity.com/paper/2204.02446/) (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)

We present an open-set logo detection (OSLD) system, which can detect (localize and recognize) any number of unseen logo classes without re-training; it only requires a small set of canonical logo images for each logo class. We achieve this using a two-stage approach: (1) Generic logo detection to detect candidate logo regions in an image. (2) Logo matching for matching the detected logo regions to a set of canonical logo images to recognize them. We constructed an open-set logo detection dataset with 12.1k logo classes and released it for research purposes.We demonstrate the effectiveness of OSLD on our dataset and on the standard Flickr-32 logo dataset, outperforming the state-of-the-art open-set and closed-set logo detection methods by a large margin. OSLD is scalable to millions of logo classes.