LGA-RCNN: Loss-Guided Attention for Object Detection

2021/04/28 by Yi Xin, Yi, Xin, Jiahao Wu +7
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2104.13763

openalex publication_date 2021/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Object detection is widely studied in computer vision filed. In recent years, certain representative deep learning based detection methods along with solid benchmarks are proposed, which boosts the development of related researchs. However, existing detection methods still suffer from undesirable performance under challenges such as camouflage, blur, inter-class similarity, intra-class variance and complex environment. To address this issue, we propose LGA-RCNN which utilizes a loss-guided attention (LGA) module to highlight representative region of objects. Then, those highlighted local information are fused with global information for precise classification and localization.

Citations

• The Pascal Visual Object Classes (VOC) Challenge
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• FCOS: Fully Convolutional One-Stage Object Detection
• MMDetection: Open MMLab Detection Toolbox and Benchmark

Related

• G-RCN: Optimizing the Gap between Classification and Localization Tasks for Object Detection
• Location-Sensitive Visual Recognition with Cross-IOU Loss
• AttentionNet: Aggregating Weak Directions for Accurate Object Detection
• LSAS: Lightweight Sub-attention Strategy for Alleviating Attention Bias Problem
• Grid R-CNN