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

[CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

Style transfer, deep learning, feature transform

A simple and lightweight genetic algorithm for optimization of any machine learning model

This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

A library for low-memory inferencing in PyTorch.

Unsupervised Foreground Extraction via Deep Region Competition

Angle data is a simple data type.

NeuralForecast is a Python library for time series forecasting with deep learning models

Neural-fractal - Create Fractals Using Complex-Valued Neural Networks!

An NLP library with Awesome pre-trained Transformer models and easy-to-use interface, supporting wide-range of NLP tasks from research to industrial applications.

PassAPI is a password generator in hash format and fully developed in Python, with the aim of teaching how to handle and build

🗣️ Microsoft Edge TTS for Home Assistant, no need for app_key

Few-Shot Object Detection via Association and DIscrimination

MODALS: Modality-agnostic Automated Data Augmentation in the Latent Space

Automatic Idiomatic Expression Detection

Code for "Training Neural Networks with Fixed Sparse Masks" (NeurIPS 2021).

Keras udrl - Keras implementation of Upside Down Reinforcement Learning

Code to generate datasets used in "How Useful is Self-Supervised Pretraining for Visual Tasks?"

Pytorch Lightning code guideline for conferences