Single-Shot Object Detection with Enriched Semantics
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is s...
| Үндсэн зохиолчид: | , , , , , |
|---|---|
| Формат: | Technical Report |
| Хэл сонгох: | en_US |
| Хэвлэсэн: |
Center for Brains, Minds and Machines (CBMM)
2018
|
| Онлайн хандалт: | http://hdl.handle.net/1721.1/115180 |
| _version_ | 1826213541184536576 |
|---|---|
| author | Zhang, Zhishuai Qiao, Siyuan Xie, Cihang Shen, Wei Wang, Bo Yuille, Alan L. |
| author_facet | Zhang, Zhishuai Qiao, Siyuan Xie, Cihang Shen, Wei Wang, Bo Yuille, Alan L. |
| author_sort | Zhang, Zhishuai |
| collection | MIT |
| description | We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image. |
| first_indexed | 2024-09-23T15:50:56Z |
| format | Technical Report |
| id | mit-1721.1/115180 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:50:56Z |
| publishDate | 2018 |
| publisher | Center for Brains, Minds and Machines (CBMM) |
| record_format | dspace |
| spelling | mit-1721.1/1151802019-04-12T22:34:11Z Single-Shot Object Detection with Enriched Semantics Zhang, Zhishuai Qiao, Siyuan Xie, Cihang Shen, Wei Wang, Bo Yuille, Alan L. We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image. This material is based upon work supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216. 2018-05-02T17:59:16Z 2018-05-02T17:59:16Z 2018-06-19 Technical Report Working Paper Other http://hdl.handle.net/1721.1/115180 en_US CBMM Memo Series;084 application/pdf Center for Brains, Minds and Machines (CBMM) |
| spellingShingle | Zhang, Zhishuai Qiao, Siyuan Xie, Cihang Shen, Wei Wang, Bo Yuille, Alan L. Single-Shot Object Detection with Enriched Semantics |
| title | Single-Shot Object Detection with Enriched Semantics |
| title_full | Single-Shot Object Detection with Enriched Semantics |
| title_fullStr | Single-Shot Object Detection with Enriched Semantics |
| title_full_unstemmed | Single-Shot Object Detection with Enriched Semantics |
| title_short | Single-Shot Object Detection with Enriched Semantics |
| title_sort | single shot object detection with enriched semantics |
| url | http://hdl.handle.net/1721.1/115180 |
| work_keys_str_mv | AT zhangzhishuai singleshotobjectdetectionwithenrichedsemantics AT qiaosiyuan singleshotobjectdetectionwithenrichedsemantics AT xiecihang singleshotobjectdetectionwithenrichedsemantics AT shenwei singleshotobjectdetectionwithenrichedsemantics AT wangbo singleshotobjectdetectionwithenrichedsemantics AT yuillealanl singleshotobjectdetectionwithenrichedsemantics |