# ProbaNet: Proposal-balanced Network for Object Detection

Source: [ProbaNet: Proposal-balanced Network for Object Detection](<https://www.sota2.com/research/paper/68fa67941e209131cea1726d>)

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

Data updated: 2025-10-25T22:18:12.808Z

Authors: Jing Wu, Xiang Zhang, Mingyi Zhou, Ce Zhu

Published: 2020-05-06T10:07:39.000Z

## Abstract

Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall performance. In this study, we propose a Proposal-balanced Network (ProbaNet) for alleviating the imbalance problem. Firstly, ProbaNet increases the probability of choosing hard samples for training by discarding easy samples through threshold truncation. Secondly, ProbaNet emphasizes foreground proposals by increasing their weights. To evaluate the effectiveness of ProbaNet, we train models based on different benchmarks. Mean Average Precision (mAP) of the model using ProbaNet achieves 1.2$\\%$ higher than the baseline on PASCAL VOC 2007. Furthermore, it is compatible with existing two-stage detectors and offers a very small amount of additional computational cost.

## 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/2005.02699>)

[PDF](<https://arxiv.org/pdf/2005.02699.pdf>)
