|
|
|
|
LEADER |
01000naa a22002652 4500 |
001 |
NLM34102919X |
003 |
DE-627 |
005 |
20231226010827.0 |
007 |
cr uuu---uuuuu |
008 |
231226s2022 xx |||||o 00| ||eng c |
024 |
7 |
|
|a 10.1109/TIP.2022.3174391
|2 doi
|
028 |
5 |
2 |
|a pubmed24n1136.xml
|
035 |
|
|
|a (DE-627)NLM34102919X
|
035 |
|
|
|a (NLM)35580106
|
040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
041 |
|
|
|a eng
|
100 |
1 |
|
|a Zhou, Linmao
|e verfasserin
|4 aut
|
245 |
1 |
0 |
|a Interactive Regression and Classification for Dense Object Detector
|
264 |
|
1 |
|c 2022
|
336 |
|
|
|a Text
|b txt
|2 rdacontent
|
337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
500 |
|
|
|a Date Revised 27.05.2022
|
500 |
|
|
|a published: Print-Electronic
|
500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
520 |
|
|
|a In object detection, enhancing feature representation using localization information has been revealed as a crucial procedure to improve detection performance. However, the localization information (i.e., regression feature and regression offset) captured by the regression branch is still not well utilized. In this paper, we propose a simple but effective method called Interactive Regression and Classification (IRC) to better utilize localization information. Specifically, we propose Feature Aggregation Module (FAM) and Localization Attention Module (LAM) to leverage localization information to the classification branch during forward propagation. Furthermore, the classifier also guides the learning of the regression branch during backward propagation, to guarantee that the localization information is beneficial to both regression and classification. Thus, the regression and classification branches are learned in an interactive manner. Our method can be easily integrated into anchor-based and anchor-free object detectors without increasing computation cost. With our method, the performance is significantly improved on many popular dense object detectors, including RetinaNet, FCOS, ATSS, PAA, GFL, GFLV2, OTA, GA-RetinaNet, RepPoints, BorderDet and VFNet. Based on ResNet-101 backbone, IRC achieves 47.2% AP on COCO test-dev, surpassing the previous state-of-the-art PAA (44.8% AP), GFL (45.0% AP) and without sacrificing the efficiency both in training and inference. Moreover, our best model (Res2Net-101-DCN) can achieve a single-model single-scale AP of 51.4%
|
650 |
|
4 |
|a Journal Article
|
700 |
1 |
|
|a Chang, Hong
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Ma, Bingpeng
|e verfasserin
|4 aut
|
700 |
1 |
|
|a Shan, Shiguang
|e verfasserin
|4 aut
|
773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 31(2022) vom: 09., Seite 3684-3696
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
773 |
1 |
8 |
|g volume:31
|g year:2022
|g day:09
|g pages:3684-3696
|
856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2022.3174391
|3 Volltext
|
912 |
|
|
|a GBV_USEFLAG_A
|
912 |
|
|
|a SYSFLAG_A
|
912 |
|
|
|a GBV_NLM
|
912 |
|
|
|a GBV_ILN_350
|
951 |
|
|
|a AR
|
952 |
|
|
|d 31
|j 2022
|b 09
|h 3684-3696
|