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

[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation

Discovering and Achieving Goals via World Models

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

eXPeditious Data Transfer

🥇Samsung AI Challenge 2021 1등 솔루션입니다🥇

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

Code related to the manuscript "Averting A Crisis In Simulation-Based Inference"

Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields.

The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

This respository includes implementations on Manifoldron: Direct Space Partition via Manifold Discovery

Calling Julia from Python - an experiment on data loading

Code for the paper "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks"

Official repository for the paper, MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding.

VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning

Driller: augmenting AFL with symbolic execution!

Deep Reinforcement Learning based autonomous navigation for quadcopters using PPO algorithm.

This is the official implementation code repository of Underwater Light Field Retention : Neural Rendering for Underwater Imaging (Accepted by CVPR Workshop2022 NTIRE)

Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data

Trained on Simulated Data, Tested in the Real World