Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection

Last update: Sep 08, 2022

Overview

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection (NimPme)

The official implementation of Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection

The code is built on TFA

Requirements

Linux with Python >= 3.6
PyTorch >= 1.4
torchvision that matches the PyTorch installation
CUDA 10.0, 10.1, 10.2
GCC >= 4.9

Getting Started

Evaluation with pre-trainied 10-shot final detecor

we provide the pre-trainied 10-shot final detecor

python3 -m tools.test_net --num-gpus 1 \
        --config-file configs/PascalVOC-detection/split1/faster_rcnn_R_101_FPN_ft_all1_10shot.yaml \
        --eval-only

Training & Evaluation in Command Line

To train a base detector, run

python3 -m tools.train_net --num-gpus 1 \
        --config-file configs/PascalVOC-detection/split1/faster_rcnn_R_101_FPN_base1.yaml

fine-tune the detector with novel set

python3 -m tools.ckpt_surgery \
        --src1 checkpoints/coco/faster_rcnn/faster_rcnn_R_101_FPN_base/model_final.pth \
        --method randinit \
        --save-dir checkpoints/coco/faster_rcnn/faster_rcnn_R_101_FPN_all
        --coco

python3 -m tools.train_net --num-gpus 1 \
        --config-file configs/COCO-detection/faster_rcnn_R_101_FPN_ft_all_1shot.yaml \
        --opts MODEL.WEIGHTS $WEIGHTS_PATH

fine-tune the detector with pseudo set

python3 -m tools.genarate_pseudo --num-gpus 1
python3 -m tools.train_feature --num-gpus 1

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection

Related tags

Overview

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection (NimPme)

Getting Started

Evaluation with pre-trainied 10-shot final detecor

Training & Evaluation in Command Line

Owner

Code for the paper "How Attentive are Graph Attention Networks?"

Lua-parser-lark - An out-of-box Lua parser written in Lark

This repository contains a re-implementation of the code for the CVPR 2021 paper "Omnimatte: Associating Objects and Their Effects in Video."

Official PyTorch implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

Official pytorch implementation of DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces

UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

Boston House Prediction Valuation Tool

DualGAN-tensorflow: tensorflow implementation of DualGAN

Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)

Official implementation of the paper DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows

“英特尔创新大师杯”深度学习挑战赛赛道3：CCKS2021中文NLP地址相关性任务

Implementation of "DeepOrder: Deep Learning for Test Case Prioritization in Continuous Integration Testing".

Pytorch version of VidLanKD: Improving Language Understanding viaVideo-Distilled Knowledge Transfer

Segmentation for medical image.

Tf alloc - Simplication of GPU allocation for Tensorflow2

Accelerated deep learning R&D

This is an unofficial implementation of the paper “Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection”.

Multi-Modal Machine Learning toolkit based on PyTorch.

UniFormer - official implementation of UniFormer

PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection

Related tags

Overview

Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection (NimPme)

Getting Started

Evaluation with pre-trainied 10-shot final detecor

Training & Evaluation in Command Line

Owner

Code for the paper "How Attentive are Graph Attention Networks?"

Lua-parser-lark - An out-of-box Lua parser written in Lark

This repository contains a re-implementation of the code for the CVPR 2021 paper "Omnimatte: Associating Objects and Their Effects in Video."

Official PyTorch implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

Official pytorch implementation of DeformSyncNet: Deformation Transfer via Synchronized Shape Deformation Spaces

UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset

Boston House Prediction Valuation Tool

DualGAN-tensorflow: tensorflow implementation of DualGAN

Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)

Official implementation of the paper DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows

“英特尔创新大师杯”深度学习挑战赛 赛道3：CCKS2021中文NLP地址相关性任务

Implementation of "DeepOrder: Deep Learning for Test Case Prioritization in Continuous Integration Testing".

Pytorch version of VidLanKD: Improving Language Understanding viaVideo-Distilled Knowledge Transfer

Segmentation for medical image.

Tf alloc - Simplication of GPU allocation for Tensorflow2

Accelerated deep learning R&D

This is an unofficial implementation of the paper “Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection”.

Multi-Modal Machine Learning toolkit based on PyTorch.

UniFormer - official implementation of UniFormer

PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

“英特尔创新大师杯”深度学习挑战赛赛道3：CCKS2021中文NLP地址相关性任务