Name: active exploration of training data for improved object detection (en Inglés)
SKU: 24564552
Price: 203.98 PEN
Availability: InStock
Author: Okuma, Kenji
ISBN: 9783848490806

portada active exploration of training data for improved object detection (en Inglés)

active exploration of training data for improved object detection (en Inglés)

Formato

Libro Físico

Autor

Kenji Okuma

Editorial

LAP Lambert Academic Publishing

Año

2012

Idioma

Inglés

N° páginas

112

Encuadernación

Tapa Blanda

Dimensiones

22.9x15.2x0.7 cm

Peso

0.18 kg.

ISBN

3848490803

ISBN13

9783848490806

Categorías

Tecnología de la información: cuestiones generales

active exploration of training data for improved object detection (en Inglés)

Kenji Okuma (Autor) · LAP Lambert Academic Publishing · Tapa Blanda

Libro Nuevo Importado

Envío: 14 a 18 días háb.

S/ 407,95S/ 203,98

-50%

Costos de importación incluídos en el precio ✅

Libro Nuevo

Quedan 40 unidades

S/ 203,98

Llega entre el 06 Oct y el 14 Oct a CERCADO DE LIMA, Lima. Seleccionar ubicación

Agregar a lista de deseos

Reseña del libro "active exploration of training data for improved object detection (en Inglés)"

This book concerns the problem of object detection, which is defined as finding all instances of an object class of interest and fitting each of them with a tight bounding window. This seemingly easy task for humans is still extremely difficult for machines. However, recent advances in object detection have enabled machines to categorize many classes of objects. Statistical models are often used for representing an object class of interest. These models learn from extensive training sets and generalize with low error rates to unseen data in a highly generic manner. But, these statistical methods have a major drawback in that they require a large amount of training data. We approach this problem by making the process of acquiring labels less tedious and less costly by reducing human labelling effort. Throughout this book, we explore means of efficient label acquisition for realizing cheaper training, faster development time, and higher-performance of object detectors.