File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-319-10578-9_41
- Scopus: eid_2-s2.0-84906489727
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Exploiting low-rank structure from latent domains for domain generalization
Title | Exploiting low-rank structure from latent domains for domain generalization |
---|---|
Authors | |
Keywords | domain adaptation domain generalization exemplar-SVMs Latent domains |
Publisher | Springer |
Citation | 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, 6-12 September 2014. In Fleet, D, Pajdla, T, Schiele, B, et al. (Eds.), Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part III, p. 628-643. Cham: Springer, 2014 How to Cite? |
Abstract | In this paper, we propose a new approach for domain generalization by exploiting the low-rank structure from multiple latent source domains. Motivated by the recent work on exemplar-SVMs, we aim to train a set of exemplar classifiers with each classifier learnt by using only one positive training sample and all negative training samples. While positive samples may come from multiple latent domains, for the positive samples within the same latent domain, their likelihoods from each exemplar classifier are expected to be similar to each other. Based on this assumption, we formulate a new optimization problem by introducing the nuclear-norm based regularizer on the likelihood matrix to the objective function of exemplar-SVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation. © 2014 Springer International Publishing. |
Persistent Identifier | http://hdl.handle.net/10722/321610 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
Series/Report no. | Lecture Notes in Computer Science ; 8691 LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Xu, Zheng | - |
dc.contributor.author | Li, Wen | - |
dc.contributor.author | Niu, Li | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:20:13Z | - |
dc.date.available | 2022-11-03T02:20:13Z | - |
dc.identifier.citation | 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, 6-12 September 2014. In Fleet, D, Pajdla, T, Schiele, B, et al. (Eds.), Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part III, p. 628-643. Cham: Springer, 2014 | - |
dc.identifier.isbn | 9783319105772 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321610 | - |
dc.description.abstract | In this paper, we propose a new approach for domain generalization by exploiting the low-rank structure from multiple latent source domains. Motivated by the recent work on exemplar-SVMs, we aim to train a set of exemplar classifiers with each classifier learnt by using only one positive training sample and all negative training samples. While positive samples may come from multiple latent domains, for the positive samples within the same latent domain, their likelihoods from each exemplar classifier are expected to be similar to each other. Based on this assumption, we formulate a new optimization problem by introducing the nuclear-norm based regularizer on the likelihood matrix to the objective function of exemplar-SVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation. © 2014 Springer International Publishing. | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Computer Vision -- ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part III | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 8691 | - |
dc.relation.ispartofseries | LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics | - |
dc.subject | domain adaptation | - |
dc.subject | domain generalization | - |
dc.subject | exemplar-SVMs | - |
dc.subject | Latent domains | - |
dc.title | Exploiting low-rank structure from latent domains for domain generalization | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-319-10578-9_41 | - |
dc.identifier.scopus | eid_2-s2.0-84906489727 | - |
dc.identifier.spage | 628 | - |
dc.identifier.epage | 643 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.publisher.place | Cham | - |