FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network (2021-08-10T00:00:00.000000Z)

TL;DR

A novel food logo detection method Multi-scale Feature Decoupling Network (MFDNet), which decouples classification and regression into two branches and focuses on the classification branch to solve the problem of distinguishing multiple food logo categories is proposed.

Abstract

Food logo detection plays an important role in the multimedia for its wide real-world applications, such as food recommendation of the self-service shop and infringement detection on e-commerce platforms. A large-scale food logo dataset is urgently needed for developing advanced food logo detection algorithms. However, there are no available food logo datasets with food brand information. To support efforts towards food logo detection, we introduce the dataset FoodLogoDet-1500, a new large-scale publicly available food logo dataset, which has 1,500 categories, about 100,000 images and about 150,000 manually annotated food logo objects. We describe the collection and annotation process of FoodLogoDet-1500, analyze its scale and diversity, and compare it with other logo datasets. To the best of our knowledge, FoodLogoDet-1500 is the first largest publicly available high-quality dataset for food logo detection. The challenge of food logo detection lies in the large-scale categories and similarities between food logo categories. For that, we propose a novel food logo detection method Multi-scale Feature Decoupling Network (MFDNet), which decouples classification and regression into two branches and focuses on the classification branch to solve the problem of distinguishing multiple food logo categories. Specifically, we introduce the feature offset module, which utilizes the deformation-learning for optimal classification offset and can effectively obtain the most representative features of classification in detection. In addition, we adopt a balanced feature pyramid in MFDNet, which pays attention to global information, balances the multi-scale feature maps, and enhances feature extraction capability. Comprehensive experiments on FoodLogoDet-1500 and other two popular benchmark logo datasets demonstrate the effectiveness of the proposed method. The code and FoodLogoDet-1500 can be found at https://github.com/hq03/FoodLogoDet-1500-Dataset.

References69 items

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

LogoDet-3K: A Large-scale Image Dataset for Logo Detection

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

End-to-End Object Detection with Transformers

The Open Brands Dataset: Unified Brand Detection and Recognition at Scale

A Novel Region of Interest Extraction Layer for Instance Segmentation

YOLOv4: Optimal Speed and Accuracy of Object Detection

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Revisiting the Sibling Head in Object Detector

Side-Aware Boundary Localization for More Precise Object Detection

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection

Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification

FoveaBox: Beyound Anchor-Based Object Detection

MMDetection: Open MMLab Detection Toolbox and Benchmark

Rethinking Classification and Localization for Object Detection

Libra R-CNN: Towards Balanced Learning for Object Detection

FCOS: Fully Convolutional One-Stage Object Detection

Feature Selective Anchor-Free Module for Single-Shot Object Detection

Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Scalable Logo Recognition Using Proxies

A Survey on Food Computing

CornerNet: Detecting Objects as Paired Keypoints

Acquisition of Localization Confidence for Accurate Object Detection

Open Logo Detection Challenge

YOLOv3: An Incremental Improvement

Path Aggregation Network for Instance Segmentation

Logo detection and recognition with synthetic images

Cascade R-CNN: Delving Into High Quality Object Detection

Open Set Logo Detection and Retrieval

Mutual Enhancement for Detection of Multiple Logos in Sports Videos

WebLogo-2M: Scalable Logo Detection by Deep Learning from the Web

Focal Loss for Dense Object Detection

Soft-NMS — Improving Object Detection with One Line of Code

Mask R-CNN

Deformable Convolutional Networks

Deep Learning for Logo Recognition

Deep Learning Logo Detection with Data Expansion by Synthesising Context

YOLO9000: Better, Faster, Stronger

Feature Pyramid Networks for Object Detection

UnitBox: An Advanced Object Detection Network

Automatic graphic logo detection via Fast Region-based Convolutional Networks

Training Region-Based Object Detectors with Online Hard Example Mining

Deep Residual Learning for Image Recognition

SSD: Single Shot MultiBox Detector

LOGO-Net: Large-scale Deep Logo Detection and Brand Recognition with Deep Region-based Convolutional Networks

On the Benefit of Synthetic Data for Company Logo Detection

DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

Very Deep Convolutional Networks for Large-Scale Image Recognition

Fast and accurate near-duplicate image search with affinity propagation on the ImageWeb