Dynamic Anchor Feature Selection for Single-Shot Object Detection

By Shuai Li, Lingxiao Yang, Jianqiang Huang, Xiansheng Hua, Lei Zhang. 2019

53 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, background): “Thereafter, plenty of works are presented to boost its performance in different aspects, such as fusing context information from different layers [24, 12, 69], training from scratch [50, 73], introducing new loss function [33, 6], anchor refinement and matching [66, 67], architecture redesign [21, 2”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, background): “Dynamic anchor feature selection for single-shot object detection [41] DAFS VGG16 512 35 (P) 33.”
Dynamic Refinement Network for Oriented and Densely Packed Object Detection (2020, background): “[19] presented a dynamic feature selection module to select pixels on basis of the position and size of new anchors.”
D2Det: Towards High Quality Object Detection and Instance Segmentation (2020, unknown): “into single-stage [35, 42, 40, 29, 27, 4] and two-stage methods [18, 43, 17, 41, 8, 21].”
CSPNet: A New Backbone that can Enhance Learning Capability of CNN (2019, unknown): “1 DAFS [16] VGG16 [32] 512×512 35 - 33.”
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation (2021, methodology): “Besides, inspired by Guided Anchor [38, 23], SipMask further aligns feature with regressed bounding boxes to improve feature representation for classification and mask coefficients generation.”