Dynamic Anchor Feature Selection for Single-Shot Object Detection

Shuai Li, Lingxiao Yang, Jianqiang Huang, Xiansheng Hua, Lei Zhang

Research output: Unpublished conference presentation (presented paper, abstract, poster)Conference presentation (not published in journal/proceeding/book)Academic researchpeer-review


The design of anchors is critical to the performance of one-stage detectors. Recently, the anchor refinement module (ARM) has been proposed to adjust the initialization of default anchors, providing the detector a better anchor reference. However, this module brings another problem: All pixels at a feature map have the same receptive field while the anchors associated with each pixel have different positions and sizes. This discordance may lead to a less effective detector. In this paper, we present a dynamic feature selection operation to select new pixels in a feature map for each refined anchor received from the ARM. The pixels are selected based on the new anchor position and size so that the receptive filed of these pixels can fit the anchor areas well, which makes the detector, especially the regression part, much easier to optimize. Furthermore, to enhance the representation ability of selected feature pixels, we design a bidirectional feature fusion module by combining features from early and deep layers. Extensive experiments on both PASCAL VOC and COCO demonstrate the effectiveness of our dynamic anchor feature selection (DAFS) operation. For the case of high IoU threshold, our DAFS can improve the mAP by a large margin.
Original languageEnglish
Number of pages10
Publication statusPublished - Nov 2019
EventIEEE International Conference on Computer Vision 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019


ConferenceIEEE International Conference on Computer Vision 2019
Abbreviated titleIEEE ICCV 2019
Country/TerritoryKorea, Republic of
Internet address


Dive into the research topics of 'Dynamic Anchor Feature Selection for Single-Shot Object Detection'. Together they form a unique fingerprint.

Cite this