File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICDM54844.2022.00105
- Scopus: eid_2-s2.0-85147734878
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Boosting Object Detection Ensembles with Error Diversity
Title | Boosting Object Detection Ensembles with Error Diversity |
---|---|
Authors | |
Keywords | n/a |
Issue Date | 2022 |
Citation | Proceedings - IEEE International Conference on Data Mining, ICDM, 2022, v. 2022-November, p. 903-908 How to Cite? |
Abstract | Object detection has played a pivotal role in numerous mission-critical applications. This paper presents a focal error diversity framework, called EDI, for strengthening the robustness of object detection ensembles under benign and adversarial scenarios. We introduce an ensemble pruning method for object detection using a novel focal error diversity measure as the robustness synergy indicator. Given a base model pool, it recommends top sub-ensembles with a smaller ensemble size yet achieving equivalent or even better mAP performance than using all available object detection models as a large ensemble. This is made possible by our negative sampling methods for object detection to capture the degree of negative correlations and the focal error diversity to measure the failure independence of component detection models in an ensemble. Extensive experiments on three object detection benchmark datasets validate that EDI effectively selects space-time efficient object detection ensembles with high mAP performance. |
Persistent Identifier | http://hdl.handle.net/10722/343406 |
ISSN | 2020 SCImago Journal Rankings: 0.545 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chow, Ka Ho | - |
dc.contributor.author | Liu, Ling | - |
dc.date.accessioned | 2024-05-10T09:07:50Z | - |
dc.date.available | 2024-05-10T09:07:50Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Proceedings - IEEE International Conference on Data Mining, ICDM, 2022, v. 2022-November, p. 903-908 | - |
dc.identifier.issn | 1550-4786 | - |
dc.identifier.uri | http://hdl.handle.net/10722/343406 | - |
dc.description.abstract | Object detection has played a pivotal role in numerous mission-critical applications. This paper presents a focal error diversity framework, called EDI, for strengthening the robustness of object detection ensembles under benign and adversarial scenarios. We introduce an ensemble pruning method for object detection using a novel focal error diversity measure as the robustness synergy indicator. Given a base model pool, it recommends top sub-ensembles with a smaller ensemble size yet achieving equivalent or even better mAP performance than using all available object detection models as a large ensemble. This is made possible by our negative sampling methods for object detection to capture the degree of negative correlations and the focal error diversity to measure the failure independence of component detection models in an ensemble. Extensive experiments on three object detection benchmark datasets validate that EDI effectively selects space-time efficient object detection ensembles with high mAP performance. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings - IEEE International Conference on Data Mining, ICDM | - |
dc.subject | n/a | - |
dc.title | Boosting Object Detection Ensembles with Error Diversity | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICDM54844.2022.00105 | - |
dc.identifier.scopus | eid_2-s2.0-85147734878 | - |
dc.identifier.volume | 2022-November | - |
dc.identifier.spage | 903 | - |
dc.identifier.epage | 908 | - |