Abstract | ||
---|---|---|
Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classifier for a target domain, where the available data is scarce. The effectiveness of the transfer is affected by the relationship between source and target. Rather than improving the learning, brute force leveraging of a source poorly related to the target may decrease the classifier performance. One strategy to reduce this negative transfer is to import knowledge from multiple sources to increase the chance of finding one source closely related to the target. This work extends the boosting framework for transferring knowledge from multiple sources. Two new algorithms, MultiSource-TrAdaBoost, and TaskTrAdaBoost, are introduced, analyzed, and applied for object category recognition and specific object detection. The experiments demonstrate their improved performance by greatly reducing the negative transfer as the number of sources increases. TaskTrAdaBoost is a fast algorithm enabling rapid retraining over new targets. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/CVPR.2010.5539857 | CVPR |
Keywords | Field | DocType |
tasktradaboost,learning (artificial intelligence),multisource tradaboost,object category recognition,boosting framework,transfer learning,brute force leveraging,object detection,object recognition,learning artificial intelligence,support vector machines,computer vision,probability distribution,testing,boosting,machine learning,data visualization,training data,algorithm design and analysis | Computer science,Transfer of learning,Artificial intelligence,Classifier (linguistics),Object detection,Computer vision,Negative transfer,Algorithm design,Pattern recognition,Support vector machine,Boosting (machine learning),Machine learning,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
2010 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4244-6984-0 | 112 | 3.16 |
References | Authors | |
20 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yi Yao | 1 | 410 | 34.59 |
Gianfranco Doretto | 2 | 1026 | 78.58 |