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.
Towards Overcoming False Positives in Visual Relationship Detection
SenseTime Research(商汤科技研究院);Beihang University(北京航空航天大学);National University of Singapore(新加坡国立大学);ByteDance AI Lab(字节跳动人工智能实验室);The Chinese University of Hong Kong(香港中文大学)
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
NGS, National University of Singapore(新加坡国立大学);ECE Department, National University of Singapore(新加坡国立大学电机与计算机工程系);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Salesforce Research Asia(Salesforce亚洲研究院)
Classification Calibration for Long-tail Instance Segmentation
National University of Singapore(新加坡国立大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);Salesforce Research Asia(Salesforce亚洲研究院)
MAFE R-CNN: Selecting More Samples to Learn Category-aware Features for Small Object Detection
School of Computer Science and Technology, Beijing Institute of Technology(计算机科学与技术学院,北京理工大学);School of Computer and Communication Engineering, University of Science and Technology Beijing(计算机与通信工程学院,北京科技大学);School of Computer Science and Technology, University of Hong Kong(计算机科学与技术学院,香港大学);Beijing Institute of Space Mechanics and Electricity(北京航天机械电子研究所);School of information and electronics, Beijing Institute of Technology(信息电子学院,北京理工大学)
Efficient Object Detection in Autonomous Driving using Spiking Neural Networks: Performance, Energy Consumption Analysis, and Insights into Open-set Object Discovery
TECNALIA(泰克纳利亚研究中心);Basque Research & Technology Alliance (BRTA)(巴斯克研究与技术联盟(BRTA));University of the Basque Country (UPV/EHU)(巴斯克大学(UPV/EHU));Deusto University(德乌斯托大学)