Abstract | ||
---|---|---|
A key topic in is the accuracy loss produced when the data distribution in the training () domain differs from that in the testing () domain. This is being recognized as a very relevant problem for many computer vision tasks such as image classification, object detection, and object category recognition. In this paper, we present a novel method that leverages multiple target domains (or sub-domains) in a hierarchical adaptation tree. The core idea is to exploit the commonalities and differences of the jointly considered target domains. Given the relevance of structural SVM (SSVM) classifiers, we apply our idea to the adaptive SSVM (A-SSVM; Xu et al., IEEE Trans Pattern Anal Mach Intell 36(12):2367–2380, ), which only requires the target domain samples together with the existing source-domain classifier for performing the desired adaptation. Altogether, we term our proposal as hierarchical A-SSVM (HA-SSVM). As proof of concept we use HA-SSVM for pedestrian detection, object category recognition and face recognition. In the former we apply HA-SSVM to the deformable part-based model (DPM; Felzenszwalb et al., IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645, ) while in the rest HA-SSVM is applied to multi-category classifiers. We will show how HA-SSVM is effective in increasing the detection/recognition accuracy with respect to adaptation strategies that ignore the structure of the target data. Since, the sub-domains of the target data are not always known a priori, we shown how HA-SSVM can incorporate sub-domain discovery for object category recognition. |
Year | DOI | Venue |
---|---|---|
2014 | https://doi.org/10.1007/s11263-016-0885-6 | International Journal of Computer Vision |
Keywords | Field | DocType |
Target Domain,Domain Adaptation,Source Domain,Pedestrian Detection,Domain Discovery | Computer science,A priori and a posteriori,Proof of concept,Artificial intelligence,Classifier (linguistics),Contextual image classification,Pedestrian detection,Facial recognition system,Computer vision,Object detection,Pattern recognition,Support vector machine,Machine learning | Journal |
Volume | Issue | ISSN |
abs/1408.5400 | 2 | 0920-5691 |
Citations | PageRank | References |
9 | 0.66 | 35 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiaolong Xu | 1 | 114 | 7.18 |
Sebastian Ramos | 2 | 9 | 0.66 |
David Vázquez | 3 | 488 | 28.04 |
Antonio M. López | 4 | 739 | 54.13 |