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

Earth Vision Foundation

OpenMMLab Image and Video Editing Toolbox

Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling

Deep Watershed Transform for Instance Segmentation

Deep Surface Reconstruction from Point Clouds with Visibility Information

Real-time ground filtering algorithm of cloud points acquired using Terrestrial Laser Scanner (TLS)

Stochastic Tensor Optimization for Robot Motion - A GPU Robot Motion Toolkit

This project aims at building a real-time wide band channel sounder using USRPs

An image classification app boilerplate to serve your deep learning models asap!

Code accompanying the paper "Wasserstein GAN"

Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting (HMNet)

Official implementation of DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations in TensorFlow 2

Pytorch implementation of Distributed Proximal Policy Optimization: https://arxiv.org/abs/1707.02286

Autonomous Movement from Simultaneous Localization and Mapping

ManipNet: Neural Manipulation Synthesis with a Hand-Object Spatial Representation - SIGGRAPH 2021

Unadversarial Examples: Designing Objects for Robust Vision

A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

arxiv-sanity, but very lite, simply providing the core value proposition of the ability to tag arxiv papers of interest and have the program recommend similar papers.

Official project repository for 'Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination'

Face recognize and crop them