Stars
LibFewShot: A Comprehensive Library for Few-shot Learning. TPAMI 2023.
Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
MDPI Journal: Remote Sensing Track 2023
Python code for texture classification based on filter banks ('S', 'LMS', 'LML', 'RFS', 'MR8')
Simple 1D CNN approach to human-activity-recognition (HAR) in PyTorch.
本实验的主要目的是基于遥感图像计算灰度共生矩阵,并基于该矩阵计算多种纹理特征。所有的计算结果已与ENVI结果进行对比,实验结果一致。
Python实现提取图像的纹理、颜色特征,包含快速灰度共现矩阵(GLCM)、LBP特征、颜色矩、颜色直方图。
deep learning for image processing including classification and object-detection etc.
Some basic image segmentation algorithms, include mean-shift, graph-based, SLIC, SEEDS, GrabCut, OneCut, et al.
Image segmentation - general superpixel segmentation & center detection & region growing
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
The official code of CVPR 2022 paper (Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation).
This repository contains lists of state-or-art weakly supervised semantic segmentation works
SC-CAM: Weakly-Supervised Semantic Segmentation via Sub-category Exploration (CVPR 2020)
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery
Code for "DoMars16k: A Diverse Dataset for Weakly Supervised Geomorphologic Analysis on Mars"
Summary of related papers on visual attention. Related code will be released based on Jittor gradually.
Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
深度学习入门教程, 优秀文章, Deep Learning Tutorial
Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning
PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).