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

Image-popularity-score - A novel deep regression method for image scoring.

Continuum Learning with GEM: Gradient Episodic Memory

[ICCV 2021] Deep Hough Voting for Robust Global Registration

Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

An unreferenced image captioning metric (ACL-21)

Bald-to-Hairy Translation Using CycleGAN

McGill Physics Hackathon 2021: Reaction-Diffusion Models for the Generation of Biological Patterns

Implements the training, testing and editing tools for "Pluralistic Image Completion"

Code and datasets for TPAMI 2021

1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

Convert Apple NeuralHash model for CSAM Detection to ONNX.

Contrastive Learning for Compact Single Image Dehazing, CVPR2021

PyTorch 1.5 implementation for paper DECOR-GAN: 3D Shape Detailization by Conditional Refinement.

Current state of supervised and unsupervised depth completion methods

A production-ready, scalable Indexer for the Jina neural search framework, based on HNSW and PSQL

Code for SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes (NeurIPS 2021)

Collapse by Conditioning: Training Class-conditional GANs with Limited Data

PyTorch implementation for "HyperSPNs: Compact and Expressive Probabilistic Circuits", NeurIPS 2021

Constructing Neural Network-Based Models for Simulating Dynamical Systems