🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

This repository is the code of the paper "Sparse Spatial Transformers for Few-Shot Learning (SCIENCE CHINA Information Sciences)".

Few Shot Object Detection Papers

Code for CVPR 2022 Oral paper: 'Few-Shot Object Detection with Fully Cross-Transformer'

Collect some papers and datastes about few-shot object detection for computer vision.

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

Code for AAAI 2022 Oral paper: 'Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment'

Code for ICCV 2021 paper: 'Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks'

Road extraction from satellite imagery

The official PyTorch implementation of the "AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection".

Hybrid attention module

Semantic Segmentation in Pytorch

[T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation

Official repo for our CVPR 22 paper: "Label, Verify, Correct: A Simple Few-Shot Object Detection Method"

Context Information Refinement for Few-Shot Object Detection in Remote Sensing Images

CVPR 2020 oral paper: Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax.

Source code for CVPR 2022 paper Sylph A Hypernetwork Framework for Few-shot Object Detection

Pytorch!!!Pytorch!!!Pytorch!!! Dynamic Convolution: Attention over Convolution Kernels (CVPR-2020)

Exploring Classification Equilibrium in Long-Tailed Object Detection, ICCV2021

Leaderboard, taxonomy, and curated list of few-shot object detection papers.

ICCV 2021 论文和开源项目合集

[ICCV 2021 Oral] Mining Latent Classes for Few-shot Segmentation

Official Implementation of Few-shot Visual Relationship Co-localization

Dynamic Relavance Learning for Few Shot Object Detection