Hierarchical Regression and Classification for Accurate Object Detection

Jiale Cao, Yanwei Pang, Jungong Han, Xuelong Li

Research output: Contribution to journalArticlepeer-review

3 Citations (SciVal)


Accurate object detection requires correct classification and high-quality localization. Currently, most of the single shot detectors (SSDs) conduct simultaneous classification and regression using a fully convolutional network. Despite high efficiency, this structure has some inappropriate designs for accurate object detection. The first one is the mismatch of bounding box classification, where the classification results of the default bounding boxes are improperly treated as the results of the regressed bounding boxes during the inference. The second one is that only one-time regression is not good enough for high-quality object localization. To solve the problem of classification mismatch, we propose a novel reg-offset-cls (ROC) module including three hierarchical steps: the regression of the default bounding box, the prediction of new feature sampling locations, and the classification of the regressed bounding box with more accurate features. For high-quality localization, we stack two ROC modules together. The input of the second ROC module is the output of the first ROC module. In addition, we inject a feature enhanced (FE) module between two stacked ROC modules to extract more contextual information. The experiments on three different datasets (i.e., MS COCO, PASCAL VOC, and UAVDT) are performed to demonstrate the effectiveness and superiority of our method. Without any bells or whistles, our proposed method outperforms state-of-the-art one-stage methods at a real-time speed. The source code is available at https://github.com/JialeCao001/HSD.

Original languageEnglish
Pages (from-to)2425-2439
Number of pages15
JournalIEEE Transactions on Neural Networks and Learning Systems
Issue number5
Early online date22 Oct 2021
Publication statusPublished - 01 May 2023


  • Detectors
  • Feature enhancement
  • Feature extraction
  • Head
  • Iron
  • Location awareness
  • Object detection
  • object detection
  • Proposals
  • reg-offset-cls (ROC) module.
  • reg-offset-cls (ROC) module


Dive into the research topics of 'Hierarchical Regression and Classification for Accurate Object Detection'. Together they form a unique fingerprint.

Cite this