# CornerNet-Lite: Efficient Keypoint Based Object Detection

arXiv: https://arxiv.org/abs/1904.08900 · HTML: https://mlsanity.com/paper/1904.08900/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2019.

## Built on by (most cited first, 24 of 24)

- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [UniHCP: A Unified Model for Human-Centric Perceptions](https://mlsanity.com/paper/2303.02936/) (2023)
- [Adaptive Class Suppression Loss for Long-Tail Object Detection](https://mlsanity.com/paper/2104.00885/) (2021)
- [Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors](https://mlsanity.com/paper/2205.14886/) (2022)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs](https://mlsanity.com/paper/2110.13713/) (2021)
- [A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey](https://mlsanity.com/paper/2208.10895/) (2022)
- [Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis](https://mlsanity.com/paper/2205.04281/) (2022)
- [YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images](https://mlsanity.com/paper/2404.06180/) (2024)
- [Continuous Human Action Recognition for Human-Machine Interaction: A Review](https://mlsanity.com/paper/2202.13096/) (2022)
- [SiamCorners: Siamese Corner Networks for Visual Tracking](https://mlsanity.com/paper/2104.07303/) (2021)
- [TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases](https://mlsanity.com/paper/2104.09123/) (2021)
- [Fewer is More: Efficient Object Detection in Large Aerial Images](https://mlsanity.com/paper/2212.13136/) (2022)
- [Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networks](https://mlsanity.com/paper/2212.11542/) (2022)
- [Towards Understanding the Effectiveness of Attention Mechanism](https://mlsanity.com/paper/2106.15067/) (2021)
- [DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation](https://mlsanity.com/paper/2312.13735/) (2023)
- [Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methods](https://mlsanity.com/paper/2408.03393/) (2024)
- [Semi-automatic 3D Object Keypoint Annotation and Detection for the Masses](https://mlsanity.com/paper/2201.07665/) (2022)
- [AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection](https://mlsanity.com/paper/2105.09596/) (2021)
- [RelationRS: Relationship Representation Network for Object Detection in Aerial Images](https://mlsanity.com/paper/2110.06730/) (2021)
- [Gastrointestinal Polyps and Tumors Detection Based on Multi-scale Feature-fusion with WCE Sequences](https://mlsanity.com/paper/2204.01012/) (2022)
- [Application-Driven AI Paradigm for Human Action Recognition](https://mlsanity.com/paper/2209.15271/) (2022)
- [Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection](https://mlsanity.com/paper/2310.05666/) (2023)

## Abstract (arXiv)

Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage detectors. However, this accuracy comes at high processing cost. In this work, we tackle the problem of efficient keypoint-based object detection and introduce CornerNet-Lite. CornerNet-Lite is a combination of two efficient variants of CornerNet: CornerNet-Saccade, which uses an attention mechanism to eliminate the need for exhaustively processing all pixels of the image, and CornerNet-Squeeze, which introduces a new compact backbone architecture. Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency. CornerNet-Saccade is suitable for offline processing, improving the efficiency of CornerNet by 6.0x and the AP by 1.0% on COCO. CornerNet-Squeeze is suitable for real-time detection, improving both the efficiency and accuracy of the popular real-time detector YOLOv3 (34.4% AP at 30ms for CornerNet-Squeeze compared to 33.0% AP at 39ms for YOLOv3 on COCO). Together these contributions for the first time reveal the potential of keypoint-based detection to be useful for applications requiring processing efficiency.