IoU-aware Single-stage Object Detector for Accurate Localization

By Shengkai Wu, Xiaoping Li, Xinggang Wang. 2019

201 citations recorded by the source corpus.

Due to the simpleness and high efficiency, single-stage object detectors have been widely applied in many computer vision applications . However, the low correlation between the classification score and localization accuracy of the predicted detections has severely hurt the localization accuracy of models. In this paper, IoU-aware single-stage object detector is proposed to solve this problem. Specifically, IoU-aware single-stage object detector predicts the IoU for each detected box. Then the classification score and predicted IoU are multiplied to compute the final detection confidence, which is more correlated with the localization accuracy. The detection confidence is then used as the input of the subsequent NMS and COCO AP computation, which will substantially improve the localization accuracy of models. Sufficient experiments on COCO and PASCAL VOC datasets demonstrate the effectiveness of IoU-aware single-stage object detector on improving model's localization accuracy. Without whistles and bells, the proposed method can substantially improve AP by $1.7\%\sim1.9\%$ and AP75 by $2.2\%\sim2.5\%$ on COCO \textit{test-dev}. On PASCAL VOC, the proposed method can substantially improve AP by $2.9\%\sim4.4\%$ and AP80, AP90 by $4.6\%\sim10.2\%$. Code is available here: {this https URL}.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Learning Open-World Object Proposals without Learning to Classify (2021, background): “standard fixed-category detection setting [14], [15], [16], [17], we discovered that a classifier-free object proposer supports cross-category and cross-dataset generalization.”
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection (2020, methodology): “the quality estimation is combined (usually multiplied) with classification confidence as final scores [12, 11, 26, 29, 35] f r the rank process of Non-Maximum Suppression (NMS) during inference.”
PP-YOLO: An Effective and Efficient Implementation of Object Detector (2020, background): “IoU Aware and Grid Sensitive will increase the post-processing time by 0.7ms and 0.1ms, since the current implementation is not efficient enough, which can be greatly reduced by merging them as a single OP in PaddlePaddle in the future.”
The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024, unknown): “The architecture of RFB Net is shown in Figure 5.”
VarifocalNet: An IoU-aware Dense Object Detector (2020, methodology): “To solve the problem, existing dense object detectors predict either an additional IoU score [11] or a centerness score [9] as the localization accuracy estimation, and multiply them by the classiﬁcation score to rank detections in NMS.”
IoU-balanced Loss Functions for Single-stage Object Detection (2019, background): “IoU-aware RetinaNet [20] attaches an IoU prediction head parallel to the regression head to predict the localization accuracy.”
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection (2020, methodology): “Following the similar paradigm, IoU-Net [13], Fitness NMS [34], MS R-CNN [12], IoUaware [36], PAA [14] utilize a separate branch to perform LQE in the IoU form.”