IoU-balanced Loss Functions for Single-stage Object Detection
By Shengkai Wu, Xiaoping Li. 2019
117 citations recorded by the source corpus.
Single-stage detectors are efficient. However, we find that the loss functions adopted by single-stage detectors are sub-optimal for accurate localization. The standard cross entropy loss for classification is independent of localization task and drives all the positive examples to learn as high classification score as possible regardless of localization accuracy during training. As a result, there will be detections that have high classification score but low IoU or low classification score but high IoU. And the detections with low classification score but high IOU will be suppressed by the ones with high classification score but low IOU during NMS, hurting the localization accuracy. For the standard smooth L1 loss, the gradient is dominated by the outliers that have poorly localization accuracy and this is harmful for accurate localization. In this work, we propose IoU-balanced loss functions that consist of IoU-balanced classification loss and IoU-balanced localization loss to solve the above problems. The IoU-balanced classification loss focuses more attention on positive examples with high IOU and can enhance the correlation between classification and localization task. The IoU-balanced localization loss decreases the gradient of the examples with low IoU and increases the gradient of examples with high IoU, which can improve the localization accuracy of models. Sufficient studies on MS COCO demonstrate that both IoU-balanced classification loss and IoU-balanced localization loss can bring substantial improvement for the single-stage detectors. Without whistles and bells, the proposed methods can improve AP by 1.1% for single-stage detectors and the improvement for AP at higher IoU threshold is especially large, such as 2.3% for AP90. The source code will be made available.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Niko Sünderhauf
- Feras Dayoub
- Haoyang Zhang
- Shuo Chen
- Xiaoping Li
- Xiaolin Hu
- Xiang-Yang Li
- Xinggang Wang
In Computer Vision and Pattern Recognition
- Jian Yang
- Luc Van Gool
- Wenhai Wang
- Niko Sünderhauf
- Jinhui Tang
- Xiang-Yang Li
- Feras Dayoub
- Xinggang Wang
Citations in the corpus
- Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection (2020, background): “Instead of introducing an additional branch, PISA [2] and IoU-balance [28] assign different weights in the classification loss based on their localization qualities, aiming at enhancing the correlation between the classification score and localization accuracy.”
- IoU-aware Single-stage Object Detector for Accurate Localization (2019, background): “Similarly, IoU-balanced classification loss [19] uses the regressed IoU to reweight the classification loss for each positive example directly and aims to make the examples with higher IoU learn higher classification score, which thus enhances the correlation between classification score and localiz”
- VarifocalNet: An IoU-aware Dense Object Detector (2020, methodology): “On the other hand, inspired by PISA [32] and IoU-balanced loss [33], we weight the positive example with the training target q .”