Scalable Object Detection for Stylized Objects

11/27/2017
by   Aayush Garg, et al.
0

Following recent breakthroughs in convolutional neural networks and monolithic model architectures, state-of-the-art object detection models can reliably and accurately scale into the realm of up to thousands of classes. Things quickly break down, however, when scaling into the tens of thousands, or, eventually, to millions or billions of unique objects. Further, bounding box-trained end-to-end models require extensive training data. Even though - with some tricks using hierarchies - one can sometimes scale up to thousands of classes, the labor requirements for clean image annotations quickly get out of control. In this paper, we present a two-layer object detection method for brand logos and other stylized objects for which prototypical images exist. It can scale to large numbers of unique classes. Our first layer is a CNN from the Single Shot Multibox Detector family of models that learns to propose regions where some stylized object is likely to appear. The contents of a proposed bounding box is then run against an image index that is targeted for the retrieval task at hand. The proposed architecture scales to a large number of object classes, allows to continously add new classes without retraining, and exhibits state-of-the-art quality on a stylized object detection task such as logo recognition.

READ FULL TEXT

page 1

page 2

page 5

research
12/24/2013

Deep learning for class-generic object detection

We investigate the use of deep neural networks for the novel task of cla...
research
07/27/2017

Exploiting Web Images for Weakly Supervised Object Detection

In recent years, the performance of object detection has advanced signif...
research
10/02/2019

DeepMark: One-Shot Clothing Detection

The one-shot approach, DeepMark, for fast clothing detection as a modifi...
research
11/04/2018

Query-based Logo Segmentation

Logo detection in real-world scene images is an important problem with u...
research
07/18/2014

LSDA: Large Scale Detection Through Adaptation

A major challenge in scaling object detection is the difficulty of obtai...
research
11/12/2015

ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks

This paper aims to classify and locate objects accurately and efficientl...
research
01/09/2022

ImageSubject: A Large-scale Dataset for Subject Detection

Main subjects usually exist in the images or videos, as they are the obj...

Please sign up or login with your details

Forgot password? Click here to reset