• Corpus ID: 240354007

PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices

  title={PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices},
  author={Guanghua Yu and Qinyao Chang and Wenyu Lv and Chang Xu and Cheng Cui and Wei Ji and Qingqing Dang and Kaipeng Deng and Guanzhong Wang and Yuning Du and Baohua Lai and Qiwen Liu and Xiaoguang Hu and Dianhai Yu and Yanjun Ma},
The better accuracy and efficiency trade-off has been a challenging problem in object detection. In this work, we are dedicated to studying key optimizations and neural network architecture choices for object detection to improve accuracy and efficiency. We investigate the applicability of the anchor-free strategy on lightweight object detection models. We enhance the backbone structure and design the lightweight structure of the neck, which improves the feature extraction ability of the… 

Figures and Tables from this paper

FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications

A novel lightweight deep learning architectures named FasterX based on YOLOX model for real-time object detection on edge GPU with better trade-off between accuracy and latency on VisDrone2021 dataset compared to state-of-the-art models.

FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs

A balanced detector driven by energy using discovered low-energy components named FemtoDet is proposed, and a new instance boundary enhancement (IBE) module for convolution optimization to overcome the contradiction between the limited capacity of CNNs and detection tasks in diverse spatial representations is developed.

Tech Report: One-stage Lightweight Object Detectors

The proposed GPU-target backbone network outperforms that of YOLOX -tiny which is selected as the benchmark by 1.43x in speed and 0.5 mAP in accuracy on NVIDIA GeForce RTX 2080 Ti GPU.

Scale-Aware Squeeze-and-Excitation for Lightweight Object Detection

This work proposes a scale-aware squeeze-and-excitation (SASE) module that utilizes SE operations to fully explore feature interactions without increasing network complexity; this is followed by a Scale-aware attention (SAA) mechanism, which adaptively fuses multiscale features by estimating the importance of each scale.

Real-time Waste Detection Algorithm Based on Optimized PicoDet

A real-time garbage detection method based on improved PicoDet, where the original CSP- PAN structure is replaced by BiFPN, and higher-level features are obtained through residual connection and weighted bidirectional feature fusion, which reduces the computational cost and accuracy while ensuring improved accuracy.

PP-YOLOE: An evolved version of YOLO

PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment is presented, using anchor-free paradigm, more pow-erful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL.

A Lightweight Sea Surface Object Detection Network for Unmanned Surface Vehicles

A lightweight object detection network based on YOLO v5.5 that achieves a better balance between speed and accuracy, which is more suitable for detecting sea surface objects for USVs is designed.

Alpha-SGANet: A multi-attention-scale feature pyramid network combined with lightweight network based on Alpha-IoU loss

An improved lightweight real-time convolutional neural network based on YOLOv5, called Alpha-SGANet: A multi-attention-scale feature pyramid network combined with a lightweight networkbased on Alpha-IoU loss, which can achieve higher accuracy with fewer parameters and has real- time speed through verification on the PASCAL VOC dataset and MS COCO dataset.

Small-Object Detection for UAV-Based Images Using a Distance Metric Method

A small-object detector for UAV-based images that can classify trained and untrained objects through object features using the distance metric method and two data augmentation strategies to enhance the diversity of the training set are designed.

Object Detection in 20 Years: A Survey

This paper extensively reviews 400+ papers of object detection in the light of its technical evolution, spanning over a quarter-century's time (from the 1990s to 2019), and makes an in-deep analysis of their challenges as well as technical improvements in recent years.



YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design

This work proposes YOLObile framework, a real-time object detection on mobile devices via compression-compilation co-design, and proposes a novel block-punched pruning scheme for any kernel size.

Searching for MobileNetV3

This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art of MobileNets.

YOLO9000: Better, Faster, Stronger

YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories, is introduced and a method to jointly train on object detection and classification is proposed, both novel and drawn from prior work.

PP-YOLO: An Effective and Efficient Implementation of Object Detector

A new object detector based on YOLOv3 that can be directly applied in actual application scenarios, rather than propose a novel detection model, and can achieve a better balance between effectiveness and efficiency than existing state-of-the-art detectors such as EfficientDet and Y OLOv4.

Focal Loss for Dense Object Detection

This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.

DetNAS: Neural Architecture Search on Object Detection

This paper proposes DetNAS to automatically search neural architectures for the backbones of object detectors, formulated into a supernet and the search method relies on evolution algorithm (EA).

You Only Look Once: Unified, Real-Time Object Detection

Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

The adopted Neural Architecture Search is adopted and a new feature pyramid architecture in a novel scalable search space covering all cross-scale connections is discovered, named NAS-FPN, which achieves better accuracy and latency tradeoff compared to state-of-the-art object detection models.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.