CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection

By Zhiwei Dong, Guoxuan Li, Yue Liao, Fei Wang, Pengju Ren, Chen Qian. 2020

179 citations recorded by the source corpus.

Keypoint-based detectors have achieved pretty-well performance. However, incorrect keypoint matching is still widespread and greatly affects the performance of the detector. In this paper, we propose CentripetalNet which uses centripetal shift to pair corner keypoints from the same instance. CentripetalNet predicts the position and the centripetal shift of the corner points and matches corners whose shifted results are aligned. Combining position information, our approach matches corner points more accurately than the conventional embedding approaches do. Corner pooling extracts information inside the bounding boxes onto the border. To make this information more aware at the corners, we design a cross-star deformable convolution network to conduct feature adaption. Furthermore, we explore instance segmentation on anchor-free detectors by equipping our CentripetalNet with a mask prediction module. On COCO test-dev, our CentripetalNet not only outperforms all existing anchor-free detectors with an AP of 48.0% but also achieves comparable performance to the state-of-the-art instance segmentation approaches with a 40.2% Mask AP. Code is available at https: //github.com/KiveeDong/CentripetalNet.

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection (2020, neutral): “4 ICCV19 CentripetalNet [5] HG-104 210 X n/a 45.”
Probabilistic two-stage detection (2021, unknown): “7 CentripetalNet (Dong et al., 2020) Hourglass-104 46.”
Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression (2021, background): “There has been growing interest in combining computer vision [31, 13, 9, 23, 15, 14, 29, 3, 4] and natural language processing [8, 45] techniques to perform vision-language cross-modal tasks [30, 38, 21, 22].”
A review of convolutional neural networks in computer vision (2024, unknown): “Dong introduced CentripetalNet (Dong et al. 2020) to address the issue that key point-based detectors are prone to matching mistakes.”
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection (2020, unknown): “CentripetalNet [6] HG-104 210 X n/a 45.”
FoveaBox: Beyound Anchor-Based Object Detection (2019, background): “Also there are some following works in bottom-up grouping manner [64], [65].”
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder (2020, unknown): “9 CentripetalNet* [6] Hourglass-104 48.”
PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection (2019, methodology): “We set α as 2 and β as 4 following the default setting in [15, 35, 4].”
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, methodology): “Our detection branch is built on top of CenterNet [10] but other anchor-free methods such as [16], [18], [47], [48] can also be used.”
RepPoints V2: Verification Meets Regression for Object Detection (2020, methodology): “Multi-task learning Several methods [11, 5, 4] adopt multi-task learning and observe moderate gain compared to the baseline.”