Scalable, High-Quality Object Detection
نویسندگان
چکیده
Current high-quality object detection approaches use the same scheme: salience-based object proposal methods followed by post-classification using deep convolutional features. This spurred recent research in improving object proposal methods [18, 32, 15, 11, 2]. However, domain agnostic proposal generation has the principal drawback that the proposals come unranked or with very weak ranking, making it hard to trade-off quality for running time. Also, it raises the more fundamental question of whether high-quality proposal generation requires careful engineering or can be derived just from data alone. We demonstrate that learning-based proposal methods can effectively match the performance of hand-engineered methods while allowing for very efficient runtime-quality trade-offs. Using our new multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with 0.5 mAP for a single model and 0.52 mAP for an ensemble of two models. MSC-Multibox significantly improves the proposal quality over its predecessor Multibox [4] method: AP increases from 0.42 to 0.53 for the ILSVRC detection challenge. Finally, we demonstrate improved bounding-box recall compared to Multiscale Combinatorial Grouping [18] with less proposals on the Microsoft-COCO [14] data set.
منابع مشابه
Application of Combined Local Object Based Features and Cluster Fusion for the Behaviors Recognition and Detection of Abnormal Behaviors
In this paper, we propose a novel framework for behaviors recognition and detection of certain types of abnormal behaviors, capable of achieving high detection rates on a variety of real-life scenes. The new proposed approach here is a combination of the location based methods and the object based ones. First, a novel approach is formulated to use optical flow and binary motion video as the loc...
متن کاملAutomatic Road Detection and Extraction From MultiSpectral Images Using a New Hierarchical Object-based Method
Road detection and Extraction is one of the most important issues in photogrammetry, remote sensing and machine vision. A great deal of research has been done in this area based on multispectral images, which are mostly relatively good results. In this paper, a novel automated and hierarchical object-based method for detecting and extracting of roads is proposed. This research is based on the M...
متن کاملCrowdsourcing Annotations for Visual Object Detection
A large number of images with ground truth object bounding boxes are critical for learning object detectors, which is a fundamental task in compute vision. In this paper, we study strategies to crowd-source bounding box annotations. The core challenge of building such a system is to effectively control the data quality with minimal cost. Our key observation is that drawing a bounding box is sig...
متن کاملObject Constellations: Scalable, Simultaneous Detection and Recognition of Multiple Specific Objects
Given a library of objects specified by example images, we describe a probabilistic framework for detecting multiple such objects in the scene, as well as estimating their positions and sizes. Detection of such an object constellation is faced with several major challenges. The approach has to be scalable to a large number of objects in the library while being robust towards outliers and noise....
متن کاملScalable photonic crystal chips for high sensitivity protein detection.
Scalable microfabrication technology has enabled semiconductor and microelectronics industries, among other fields. Meanwhile, rapid and sensitive bio-molecule detection is increasingly important for drug discovery and biomedical diagnostics. In this work, we designed and demonstrated that photonic crystal sensor chips have high sensitivity for protein detection and can be mass-produced with sc...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1412.1441 شماره
صفحات -
تاریخ انتشار 2014