QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

By Chenhongyi Yang, Zehao Huang, Naiyan Wang. Computer Vision and Pattern Recognition, 2021

450 citations recorded by the source corpus.

While general object detection with deep learning has achieved great success in the past few years, the performance and efficiency of detecting small objects are far from satisfactory. The most common and effective way to promote small object detection is to use high-resolution images or feature maps. However, both approaches induce costly computation since the computational cost grows squarely as the size of images and features increases. To get the best of two worlds, we propose QueryDet that uses a novel query mechanism to accelerate the inference speed of feature-pyramid based object detectors. The pipeline composes two steps: it first predicts the coarse locations of small objects on low-resolution features and then computes the accurate detection results using high-resolution features sparsely guided by those coarse positions. In this way, we can not only harvest the benefit of high-resolution feature maps but also avoid useless computation for the background area. On the popular COCO dataset, the proposed method improves the detection mAP by 1.0 and mAP-small by 2.0, and the high-resolution inference speed is improved to 3.0× on average. On VisDrone dataset, which contains more small objects, we create a new state-of-the-art while gaining a 2.3× high-resolution acceleration on average. Code is available at https://github.com/ChenhongyiYang/QueryDet=PyTorch.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/70b94593c34cd5a323a1dfb037df6af00a7ac00b

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

1. Ke Yan
2. Xiang Yuan
3. Gong Cheng
4. Qinghua Zeng
5. Xiwen Yao
6. Junwei Han
7. Muhammad Hussain

In Computer Vision and Pattern Recognition

1. Gong Cheng
2. Junwei Han
3. Xiwen Yao
4. Ke Yan
5. Xiang Yuan
6. Qinghua Zeng
7. Peicheng Zhou
8. Lei Guo

Citations in the corpus

• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, background): “QueryDet [77] designs the cascade query strategy to avoid the redundant computation on low-level features, making it possible to detect small objects on high-resolution feature maps efficiently.”