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 reproducing our analysis in the paper titled: Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

A Demo server serving Bert through ONNX with GPU written in Rust with <3

AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data

Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation

Codes of the paper Deformable Butterfly: A Highly Structured and Sparse Linear Transform.

[ACM MM 2019 Oral] Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation

Advantage Actor Critic (A2C): jax + flax implementation

Deep Federated Learning for Autonomous Driving

Source Code for ICSE 2022 Paper - ``Can We Achieve Fairness Using Semi-Supervised Learning?''

Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)

PyTorch common framework to accelerate network implementation, training and validation

Code accompanying paper: Meta-Learning to Improve Pre-Training

CoRe: Contrastive Recurrent State-Space Models

Self-Supervised Learning for Domain Adaptation on Point-Clouds

OpenGAN: Open-Set Recognition via Open Data Generation

Implicit Deep Adaptive Design (iDAD)

Python scripts using the Mediapipe models for Halloween.

Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification

Yggdrasil - A simplistic bot designed to streamline your server experience

Single-Stage Instance Shadow Detection with Bidirectional Relation Learning (CVPR 2021 Oral)