AP-Loss for Accurate One-Stage Object Detection

Abstract

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We provide in-depth analyses on the good convergence property and computational complexity of the proposed algorithm, both theoretically and empirically. Experimental results demonstrate notable improvement in addressing the imbalance issue in object detection over existing AP-based optimization algorithms. An improved state-of-the-art performance is achieved in one-stage detectors based on AP-loss over detectors using classification-losses on various standard benchmarks. The proposed framework is also highly versatile in accommodating different network architectures. Code is available at https://github.com/cccorn/AP-loss .

arXiv commentAccepted to IEEE TPAMI. arXiv admin note: substantial text overlap with arXiv:1904.06373

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• DSSD : Deconvolutional Single Shot Detector
• Towards Accurate One-Stage Object Detection with AP-Loss
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• Training Deep Neural Networks via Direct Loss Minimization

Cited by in corpus (6)

• A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
• Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence
• GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
• Rank & Sort Loss for Object Detection and Instance Segmentation
• AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks
• Deep AUC Maximization for Medical Image Classification: Challenges and Opportunities