CenterNet: Keypoint Triplets for Object Detection

By Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, Qi Tian. 2019

3,464 citations recorded by the source corpus.

In object detection, keypoint-based approaches often experience the drawback of a large number of incorrect object bounding boxes, arguably due to the lack of an additional assessment inside cropped regions. This paper presents an efficient solution that explores the visual patterns within individual cropped regions with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules, cascade corner pooling, and center pooling, that enrich information collected by both the top-left and bottom-right corners and provide more recognizable information from the central regions. On the MS-COCO dataset, CenterNet achieves an AP of 47.0 %, outperforming all existing one-stage detectors by at least 4.9%. Furthermore, with a faster inference speed than the top-ranked two-stage detectors, CenterNet demonstrates a comparable performance to these detectors. Code is available at https://github.com/Duankaiwen/CenterNet.

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

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, methodology): “CenterNet [11] extends CornetNet as a triplet rather than a pair of keypoints to improve both precision and re-call.”
Exploring Plain Vision Transformer Backbones for Object Detection (2022, neutral): “anchor-free [30,14,49], and region-based [20,25,19,46] vs.”
Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark (2021, background): “Recently, anchor-free approaches have at-tracted wide attention of researchers by using key points to represent the objects, including CornerNet [15], CenterNet [6], and FCOS [34].”
Novel Class Discovery without Forgetting (2022, background): “Over the last decade, deep learning algorithms have achieved remarkable performances on multiple computer vision tasks [15,37,50,7,45], even outperforming humans on many of them.”
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection (2020, neutral): “1 ICCV19 CenterNet [6] HG-104 190 X 3.”
Deep High-Resolution Representation Learning for Visual Recognition (2019, methodology): “The results are obtained from MMDetection [17]. tection performance on COCO val . under two anchor-based frameworks: Faster R-CNN [118] and Cascade R-CNN [12], and two recently-developed anchor-free frameworks: FCOS [136] and CenterNet [36].”
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (2019, neutral): “[19] exploit instance centers for object detection.”
Dynamic Head: Unifying Object Detection Heads with Attentions (2021, background): “[9] further improved the performance by detecting each object as a triplet, rather than a pair of key-points to reduce incorrect predictions.”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, methodology): “◦ RPN [64], SSD [50], YOLO [61], RetinaNet [45] (anchor based) ◦ CornerNet [37], CenterNet [13], MatrixNet [60], FCOS [78] (anchor free)”
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking (2020, methodology): “Inspired by Zhou et al. (2019a, b), Law and Deng (2018), Duan et al. (2019), the detection branch is implemented in an anchor-free style which estimates object centers and sizes represented as position-awaremeasurement maps.”
Spacing Loss for Discovering Novel Categories (2022, background): “Availability of large amount of annotated data has fueled unprecedented success of deep learning in various machine learning tasks [5, 9, 18, 30, 36, 37].”
Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, background): “CornerNet [17], FCOS [36], CenterNet [7] and ExtremeNet [57] attempt to predict some keypoints of objects such as corners or extreme points, which are then grouped into bounding boxes.”
SOLQ: Segmenting Objects by Learning Queries (2021, background): “Some recent works [8, 9, 10, 11] build instance segmentation frameworks on top of anchor-free object detectors [12, 13] to remove the ROI-Cropping operation, reducing the effect of feature misalignment.”
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS (2023, methodology): “YOLOX, inspired by anchor-free state-of-the-art object detectors such as CornerNet [91], CenterNet [92], and FCOS [93], returned to an anchor-free architecture simplifying the training and decoding process.”
FoveaBox: Beyound Anchor-Based Object Detection (2019, background): “Another family of anchor-free methods follow the ‘bottom-up’ way [61], [62].”
Arbitrary-Oriented Object Detection with Circular Smooth Label (2020, background): “CornerNet [15], CenterNet [5] and ExtremeNet [48] attempt to predict some keypoints of objects such as corners or extreme points, which are then grouped into bounding boxes.”
PolarMask: Single Shot Instance Segmentation With Polar Representation (2019, background): “Recent trends in the vision community have spent more effort in designing simpler pipelines of bounding box detectors [17, 23, 29, 31, 33, 10, 19] and subsequent instance-wise recognition tasks including instance segmentation [2, 4, 34], which is also the main focus of our work here.”
FreeAnchor: Learning to Match Anchors for Visual Object Detection (2019, background): “3 CenterNet [15] Hourglass-104 480k 44.”