Towards Accurate One-Stage Object Detection With AP-Loss
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5114-5122
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 verify good convergence property of the proposed algorithm theoretically and empirically. Experimental results demonstrate notable performance improvement in state-of-the-art one-stage detectors based on AP-loss over different kinds of classification-losses on various benchmarks, without changing the network architectures.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Feature Pyramid Networks for Object Detection2017
- YOLO9000: Better, Faster, Stronger2017
- Deep Residual Learning for Image Recognition2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Training Region-Based Object Detectors with Online Hard Example Mining2016
- Fast R-CNN2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Learning the unlearnableJournal of Physics A: General Physics, 1995
- The AdaTron: An Adaptive Perceptron AlgorithmEurophysics Letters, 1989
- Learning algorithms with optimal stability in neural networksJournal of Physics A: General Physics, 1987