Pinned Repositories
1xN
1xN Block Pattern for Network Sparsity
AAL-pruning
Filter Pruning for Deep Convolutional Neural Networks via Auxiliary Attention
DW
A Dual Weighting Label Assignment Scheme for Object Detection
DyRep
Official implementation for paper "DyRep: Bootstrapping Training with Dynamic Re-parameterization", CVPR 2022
GASN
A Novel Guided Anchor Siamese Network for Arbitrary Target-Of-Interest Tracking in Video-SAR
LPNet-PyTorch
This repository is a PyTorch version of the paper "Luminance-aware Pyramid Network for Low-light Image Enhancement" (TMM 2020).
ResamplingNet
ResamplingNet: End-to-End Adaptive Feature Resampling Network for Real-Time Aerial Tracking
Restoring-Extremely-Dark-Images-In-Real-Time
The project is the official implementation of our CVPR 2021 paper, "Restoring Extremely Dark Images in Real Time"
StreamYOLO
Real-time Object Detection for Streaming Perception, CVPR 2022
Ultra-Fast-Lane-Detection-v2-plus
based on ufld-v2
scott-mao's Repositories
scott-mao/DDRNet
The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"
scott-mao/ELLIE
Exposedness based Noise-Suppressing Low-Light Image Enhancement
scott-mao/NonLatinPhotoOCR
Towards Boosting the Accuracy of Non-Latin Scene Text Recognition
scott-mao/TD-SiamRPN
A Template-driven Siamese Region Proposal Network for Visual Tracking
scott-mao/A-MNS_TemplateMatching
Fast and robust template matching with majority neighbour similarity and annulus projection transformation
scott-mao/BSRGAN
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the testing code!
scott-mao/cascade-sr
Implementation of "Cascade Convolutional Neural Network for Image Super-Resolution" Paper
scott-mao/centerdet
scott-mao/ComputeLibrary
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
scott-mao/CSACF
Title: Color-Saliency-Aware Correlation Filters with Approximate Affine Transform for Visual Tracking
scott-mao/Face-NMS
Official implementation of "Face-NMS: A Core-set Selection Approach for Efficient Face Recognition"
scott-mao/FPAN
flow-based multi-head attention network for single image stochastic super-resolution
scott-mao/IrwGAN
Official pytorch implementation of the ICCV paper
scott-mao/LAU-Net
This repo is the official pytorch implement for LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution (CVPR, 2021).
scott-mao/LeapMotionGestureClassifier
Currently this is a toy implementation of a leap motion dynamic hand gesture classifier.
scott-mao/light-reid
[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x
scott-mao/Lightweight-SSD-Real-time-Lightweight-Single-Shot-Detector-for-Mobile-Devices
scott-mao/Low-Light-Image-Enhancement-using-DarkEDNet
Here we designed a CNN based model which would enhance a low light image.
scott-mao/MC-Denoising-via-Auxiliary-Feature-Guided-Self-Attention
Official implementation of MC Denoising via Auxiliary Feature Guided Self-Attention (SIGGRAPH Asia 2021 paper)
scott-mao/MODNet
A Trimap-Free Solution for Portrait Matting in Real Time
scott-mao/PLabel
半自动标注系统是基于BS架构，由鹏城实验室叶齐翔教授团队自主研发，集成视频抽帧，目标检测、视频跟踪、ReID分类、人脸检测等算法，实现了对图像，视频的自动标注，并可以对自动算法的结果进行人工标注，最终得到标注结果，同时也可以对视频、图片、医疗（包括dicom文件及病理图像）相关的数据进行人工标注，标注结果支持COCO及VOC格式。支持多人协同标注。 半自动标注系统主要功能有：用户管理，数据集管理，自动标注，人工标注，ReID标注，车流统计，视频标注，医疗CT标注，超大图像标注，模型管理与重训，报表管理。数据标注过程一个非常重要的因素是数据安全，在标注使用中防止数据泄露，采用基于web标注工具是有效避免数据泄露的措施之一。 半自动标注系统以保证性能的情况下最小化人工标注代价为目标，不断提升自动标注效率，减少人工标注和人工参与过程。
scott-mao/pruning-vs-xnor
Official repository for the research article "Pruning vs XNOR-Net: A ComprehensiveStudy on Deep Learning for AudioClassification in Microcontrollers"
scott-mao/pseudopruner
A PyTorch based DCNN channel/filter pruning implementation with virtual pruning. Realistic inference effect, no real speed-up.
scott-mao/PSS-Net
scott-mao/SSLD
A Generalized Network Based on Multi-scale Densely Connection and Residual Attention for Sound Source Localization and Detection
scott-mao/TVDCM
scott-mao/Yolo-FastestV2
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
scott-mao/YOLO_Universal_Anatomical_Landmark_Detection
Code and dataset for "You Only Learn Once: Universal Anatomical Landmark Detection" https://arxiv.org/pdf/2103.04657
scott-mao/YOLOv5-Lite
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
scott-mao/yolov5_prune_sfp