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

Apply AnimeGAN-v2 across frames of a video clip

This is an early in-development version of training CLIP models with hivemind.

a Pytorch easy re-implement of "YOLOX: Exceeding YOLO Series in 2021"

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation (CoRL 2021)

A collection of resources and papers on Diffusion Models, a darkhorse in the field of Generative Models

Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it

Cosine Annealing With Warmup

Learning to See by Looking at Noise

A clean and robust Pytorch implementation of PPO on continuous action space.

U-Net Brain Tumor Segmentation

TF2 implementation of knowledge distillation using the "function matching" hypothesis from the paper Knowledge distillation: A good teacher is patient and consistent by Beyer et al.

Reimplementation of NeurIPS'19: "Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting" by Shu et al.

TensorFlow (v2.7.0) benchmark results on an M1 Macbook Air 2020 laptop (macOS Monterey v12.1).

Advantage Actor Critic (A2C): jax + flax implementation

Self-supervised Label Augmentation via Input Transformations (ICML 2020)

Training BERT with Compute/Time (Academic) Budget

Tidy interface to polars

A Pytorch Implementation of ClariNet

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

A Re-implementation of the paper "A Deep Learning Framework for Character Motion Synthesis and Editing"