Rethinking Classification and Localization for Object Detection

  title={Rethinking Classification and Localization for Object Detection},
  author={Yue Wu and Yinpeng Chen and Lu Yuan and Zicheng Liu and Lijuan Wang and Hongzhi Li and Yun Raymond Fu},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Yue Wu, Yinpeng Chen, Y. Fu
  • Published 13 April 2019
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures work for these two tasks. To address this issue, we perform a thorough analysis and find an interesting fact that the two head structures have opposite preferences towards the two tasks. Specifically, the fully connected head (fc-head) is more suitable for the… 

Exploring Contextual Relationships for Cervical Abnormal Cell Detection

Experiments conducted on a large cervical cell detection dataset reveal that the introduction of RRAM and GRAM both achieves better average precision (AP) than the baseline methods and the method outperforms the state-of-the-art (SOTA) methods.

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

A Large-Scale SAR Ship detection dataset from Sentinel-1 and a Pure Background Hybrid Training mechanism (PBHT-mechanism) to suppress false alarms of land in large-scale SAR images to inspire related scholars to make extensive research into SAR ship detection methods with engineering application value.

Density and Context Aware Network with Hierarchical Head for Traffic Scene Detection

A novel detector called Density and Context Aware Network(DCANet) that can focus on dense regions and adaptively aggregate context features and classify and locate imbalanced objects employed in hierarchical heads is proposed.

Object affordance detection with boundary-preserving network for robotic manipulation tasks

A boundary-preserving network (BPN) is proposed to provide affordance masks with better boundary quality for robots to manipulate objects and experiments show that this method is helpful to improve the boundary quality of the predicted affordance mask results.

View-Disentangled Transformer for Brain Lesion Detection

A novel view-disentangled transformer is proposed to enhance the extraction of MRI features for more accurate tumour detection and performs well for brain lesion detection on a challenging brain MRI dataset.

Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization

This work finds that classification and regression have different sensitivities to the object translation, from the investigation about the availability of highly overlapping proposals, and proposes a decoupled sampling strategy for a deep detector, named Decoupled R-CNN.

Align Deep Features for Oriented Object Detection

A single-shot alignment network (S2A-Net) consisting of two modules: a feature alignment module (FAM) and an oriented detection module (ODM) that can achieve the state-of-the-art performance on two commonly used aerial objects’ data sets while keeping high efficiency.

FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications

A novel lightweight deep learning architectures named FasterX based on YOLOX model for real-time object detection on edge GPU with better trade-off between accuracy and latency on VisDrone2021 dataset compared to state-of-the-art models.

One-Stage Arbitrary-Oriented Object Detection With Prediction Decoupling

This study explores feature misalignment among sub-tasks in one-stage arbitrary-oriented object detection and finds that there are relevance and conflicts among the features of category prediction, foreground score prediction, orientation prediction and boundary prediction.