Semi-Supervised Self-Training of Object Detection Models

نویسندگان

  • Chuck Rosenberg
  • Martial Hebert
  • Henry Schneiderman
چکیده

The construction of appearance-based object detection systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled in order to capture variations in object appearance. Semi-supervised training is a means for reducing the effort needed to prepare the training set by training the model with a small number of fully labeled examples and an additional set of unlabeled or weakly labeled examples. In this work we present a semi-supervised approach to training object detection systems based on self-training. We implement our approach as a wrapper around the training process of an existing object detector and present empirical results. The key contributions of this empirical study is to demonstrate that a model trained in this manner can achieve results comparable to a model trained in the traditional manner using a much larger set of fully labeled data, and that a training data selection metric that is defined independently of the detector greatly outperforms a selection metric based on the detection confidence generated by the detector.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Semi-Supervised Training of Models for Appearance-Based Statistical Object Detection Methods

Appearance-based object detection systems using statistical models have proven quite successful. They can reliably detect textured, rigid objects in a variety of poses, lighting conditions and scales. However, the construction of these systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled in order to capture variations in obje...

متن کامل

Data Distillation: Towards Omni-Supervised Learning

We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lowerbounded by performance on existing labeled datasets, offering the potential to surpass state-of-the-art fully supervised methods. To exploit the omni-supervised setting, we p...

متن کامل

Fisher Discriminant Analysis (FDA), a supervised feature reduction method in seismic object detection

Automatic processes on seismic data using pattern recognition is one of the interesting fields in geophysical data interpretation. One part is the seismic object detection using different supervised classification methods that finally has an output as a probability cube. Object detection process starts with generating a pickset of two classes labeled as object and non-object and then selecting ...

متن کامل

A Semi-Supervised Learning Algorithm Based on Modified Self-training SVM

In this paper, we first introduce some facts about semi-supervised learning and its often used methods such as generative mixture models, self-training, co-training and Transductive SVM and so on. Then we present a self-training semi-supervised SVM algorithm based on which we give out a modified algorithm. In order to demonstrate its validity and effectiveness, we carry out some experiments whi...

متن کامل

Filling the Gap: Semi-Supervised Learning for Opinion Detection Across Domains

We investigate the use of Semi-Supervised Learning (SSL) in opinion detection both in sparse data situations and for domain adaptation. We show that co-training reaches the best results in an in-domain setting with small labeled data sets, with a maximum absolute gain of 33.5%. For domain transfer, we show that self-training gains an absolute improvement in labeling accuracy for blog data of 16...

متن کامل

ذخیره 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 نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005