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

Official Pytorch implementation of "Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video", CVPR 2021

Computer Vision is an elective course of MSAI, SCSE, NTU, Singapore

Another pytorch implementation of FCN (Fully Convolutional Networks)

Code for our CVPR 2022 Paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection"

Cache Requests in Deta Bases and Echo them with Deta Micros

This is the official code for the paper "Ad2Attack: Adaptive Adversarial Attack for Real-Time UAV Tracking".

Image Classification - A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

Mosaic of Object-centric Images as Scene-centric Images (MosaicOS) for long-tailed object detection and instance segmentation.

🐸STT integration examples

Source code for our paper "Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures"

Densely Connected Search Space for More Flexible Neural Architecture Search (CVPR2020)

Data and analysis code for an MS on SK VOC genomes phenotyping/neutralisation assays

GNNAdvisor: An Efficient Runtime System for GNN Acceleration on GPUs

A CV toolkit for my papers.

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)

Accelerated deep learning R&D

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

Source code of D-HAN: Dynamic News Recommendation with Hierarchical Attention Network