TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors
Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors. To accurately detect small objects with limited computation, we propose a two-stage lightweight detection framework with extremely low computation complexity, termed as TinyDet. It enables high-resolution feature maps for dense anchoring to better cover small objects, proposes a sparsely-connected convolution for computation reduction, enhances the early stage features in the backbone, and addresses the feature misalignment problem for accurate small object detection. On the COCO benchmark, our TinyDet-M achieves 30.3 AP and 13.5 AP^s with only 991 MFLOPs, which is the first detector that has an AP over 30 with less than 1 GFLOPs; besides, TinyDet-S and TinyDet-L achieve promising performance under different computation limitation.
Code (0)
등록된 구현이 없습니다.
Tasks
object-detectionObject DetectionSmall Object DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
High-order Spatial Interactions Enhanced Lightweight Model for Optical Remote Sensing Image-based Small Ship Detection
Accurate and reliable optical remote sensing image-based small-ship detection is crucial for maritime surveillance systems, but existing methods often struggle with balancing detection performance and computational compl…
object-detectionObject DetectionSmall Object DetectionYolovN-CBi: A Lightweight and Efficient Architecture for Real-Time Detection of Small UAVs
Unmanned Aerial Vehicles, commonly known as, drones pose increasing risks in civilian and defense settings, demanding accurate and real-time drone detection systems. However, detecting drones is challenging because of th…
Knowledge DistillationSmall Object DetectionFrom Blurry to Brilliant Detection: YOLOv5-Based Aerial Object Detection with Super Resolution
The demand for accurate object detection in aerial imagery has surged with the widespread use of drones and satellite technology. Traditional object detection models, trained on datasets biased towards large objects, str…
Objectobject-detectionObject DetectionSuper-ResolutionTowards lightweight convolutional neural networks for object detection
We propose model with larger spatial size of feature maps and evaluate it on object detection task. With the goal to choose the best feature extraction network for our model we compare several popular lightweight network…
CPUObjectobject-detectionObject Detection+1HierLight-YOLO: A Hierarchical and Lightweight Object Detection Network for UAV Photography
The real-time detection of small objects in complex scenes, such as the unmanned aerial vehicle (UAV) photography captured by drones, has dual challenges of detecting small targets (<32 pixels) and maintaining real-time …
Small Object Detection