ChunyanZhao
Follow
Stars
SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention.
[CVPR2023 Highlight] Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
A Supervised and Semi-Supervised Object Detection Library for YOLO Series
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
中文版面检测（Chinese layout detection），yolov8 is used to detect the layout of Chinese document images。
YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection
A curated list of awesome resources for generic object detection in aerial images.
An official implementation of paper "Paragraph2Graph: A Language-independent GNN-based framework for layout analysis"
This is the official pytorch implementation of "FourLLIE: Boosting Low-Light Image Enhancement by Fourier Frequency Information" (ACM MM 2023)
Python implementation of two low-light image enhancement techniques via illumination map estimation
🔥CDIoU and CDIoU loss is like a convenient plug-in that can be used in multiple models. CDIoU and CDIoU loss have different excellent performances in several models such as Faster R-CNN, YOLOv4, Re…
Official implementation of the paper: "Narotamo, H., Sanches, J. M., & Silveira, M. (2019, July). Segmentation of Cell Nuclei in Fluorescence Microscopy Images Using Deep Learning. "
一些关于目标检测的脚本的改进思路代码，详细请看readme.md
[ICCV 2023] Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes
[ECCV 2022] Robust Object Detection With Inaccurate Bounding Boxes
Improved YOLOv5 for Small Object Detection,
Point based and tiny object detection and localization code set of UCAS-VG
Visualizing Yolov5's layers using GradCam
Official code for "BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification"
这是各个主干网络分类模型的源码，可以用于训练自己的分类模型。
Universal Representation Learning from Multiple Domains for Few-shot Classification - ICCV 2021, Cross-domain Few-shot Learning with Task-specific Adapters - CVPR 2022
Code for: "Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes" and "TaskNorm: Rethinking Batch Normalization for Meta-Learning"
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation (ICLR 2020 spotlight)
Official PyTorch Implementation of DIaM in "A Strong Baseline for Generalized Few-Shot Semantic Segmentation" (CVPR 2023)
Repository for the CVPR-2023 paper : StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning