# PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection

Source: [PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection](<https://www.sota2.com/research/paper/68fa66371e209131cea0edbb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:44:30.600Z

Authors: Qiankun Tang, Shice Liu, Jie Li, Yu Hu

Published: 2019-08-09T03:29:15.000Z

## Abstract

We introduce a novel single-shot object detector to ease the imbalance of foreground-background class by suppressing the easy negatives while increasing the positives. To achieve this, we propose an Anchor Promotion Module (APM) which predicts the probability of each anchor as positive and adjusts their initial locations and shapes to promote both the quality and quantity of positive anchors. In addition, we design an efficient Feature Alignment Module (FAM) to extract aligned features for fitting the promoted anchors with the help of both the location and shape transformation information from the APM. We assemble the two proposed modules to the backbone of VGG-16 and ResNet-101 network with an encoder-decoder architecture. Extensive experiments on MS COCO well demonstrate our model performs competitively with alternative methods (40.0\\% mAP on \\textit{test-dev} set) and runs faster (28.6 \\textit{fps}).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1908.03295>)

[PDF](<https://arxiv.org/pdf/1908.03295.pdf>)