Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

Last update: Dec 31, 2022

Related tags

Overview

This repo is the official implementation of "Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework".

@inproceedings{zhou2021instant,
  title={Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework},
  author={Zhou, Qiang and Yu, Chaohui and Wang, Zhibin and Qian, Qi and Li, Hao},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4081--4090},
  year={2021}
}

The code is based on MMdetection Toolbox.

1. Install

conda create -n instant_teaching python=3.7 -y
conda activate instant_teaching
conda install pytorch=1.7.1 torchvision cudatoolkit=10.1 -c pytorch
pip install mmcv==1.2.4

git clone http://gitlab.alibaba-inc.com/jianchong.zq/InstantTeaching.git
cd InstantTeaching
pip install -v -e .

2. Prepare COCO Dataset for Semi-Supervised Learning

mkdir -p datasets/coco
ln -s [coco_2017_downloaded] datasets/coco/coco_2017

python projects/InstantTeaching/tools/split_coco.py datasets/coco/coco_2017/annotations/instances_train2017.json 10

Two files of instances_train2017_10_labeled.json and instances_train2017_90_unlabeled.json will be generated.

3. Training

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch \
    --nproc_per_node=8 --master_port=1234 tools/train.py \
    projects/InstantTeaching/configs/instant_teaching_two_stage_r50_coco_quick_10.py \
    --launcher pytorch \
    --work-dir ${output_dir} \
    --no-validate

Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

Related tags

Overview

1. Install

2. Prepare COCO Dataset for Semi-Supervised Learning

3. Training

Owner

Implementation for "Conditional entropy minimization principle for learning domain invariant representation features"

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park, Rares Ambrus, Vitor Guizilini, Jie Li, and Adrien Gaidon.

A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

Applying PVT to Semantic Segmentation

Implements an infinite sum of poisson-weighted convolutions

KwaiRec: A Fully-observed Dataset for Recommender Systems (Density: Almost 100%)

Does Pretraining for Summarization Reuqire Knowledge Transfer?

The BCNet related data and inference model.

Implementation for Shape from Polarization for Complex Scenes in the Wild

The official implementation code of "PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction."

A PaddlePaddle version of Neural Renderer, refer to its PyTorch version

The official PyTorch code implementation of "Personalized Trajectory Prediction via Distribution Discrimination" in ICCV 2021.

PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

code release for USENIX'22 paper `On the Security Risks of AutoML`

A list of Machine Learning Art Colabs

A Deep Reinforcement Learning Framework for Stock Market Trading

RLDS stands for Reinforcement Learning Datasets

In this project we predict the forest cover type using the cartographic variables in the training/test datasets.

Computer-Vision-Paper-Reviews - Computer Vision Paper Reviews with Key Summary along Papers & Codes

Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

Related tags

Overview

1. Install

2. Prepare COCO Dataset for Semi-Supervised Learning

3. Training

Owner

Implementation for "Conditional entropy minimization principle for learning domain invariant representation features"

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.

A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

Applying PVT to Semantic Segmentation

Implements an infinite sum of poisson-weighted convolutions

KwaiRec: A Fully-observed Dataset for Recommender Systems (Density: Almost 100%)

Does Pretraining for Summarization Reuqire Knowledge Transfer?

The BCNet related data and inference model.

Implementation for Shape from Polarization for Complex Scenes in the Wild

The official implementation code of "PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction."

A PaddlePaddle version of Neural Renderer, refer to its PyTorch version

The official PyTorch code implementation of "Personalized Trajectory Prediction via Distribution Discrimination" in ICCV 2021.

PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

code release for USENIX'22 paper `On the Security Risks of AutoML`

A list of Machine Learning Art Colabs

A Deep Reinforcement Learning Framework for Stock Market Trading

RLDS stands for Reinforcement Learning Datasets

In this project we predict the forest cover type using the cartographic variables in the training/test datasets.

Computer-Vision-Paper-Reviews - Computer Vision Paper Reviews with Key Summary along Papers & Codes

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park, Rares Ambrus, Vitor Guizilini, Jie Li, and Adrien Gaidon.