Focal and Global Knowledge Distillation for Detectors

Last update: Dec 23, 2022

Related tags

Deep Learning FGD

Overview

FGD

Paper: Focal and Global Knowledge Distillation for Detectors

Install MMDetection and MS COCO2017

Our codes are based on MMDetection. Please follow the installation of MMDetection and make sure you can run it successfully.
This repo uses mmdet==2.11.0 and mmcv-full==1.2.4

Add and Replace the codes

Add the configs/. in our codes to the configs/ in mmdetectin's codes.
Add the mmdet/distillation/. in our codes to the mmdet/ in mmdetectin's codes.
Replace the mmdet/apis/train.py and tools/train.py in mmdetection's codes with mmdet/apis/train.py and tools/train.py in our codes.
Add pth_transfer.py to mmdetection's codes.
Unzip COCO dataset into data/coco/

Train

#single GPU
python tools/train.py configs/distillers/fgd/fgd_retina_rx101_64x4d_distill_retina_r50_fpn_2x_coco.py

#multi GPU
bash tools/dist_train.sh configs/distillers/fgd/fgd_retina_rx101_64x4d_distill_retina_r50_fpn_2x_coco.py 8

Transfer

# Tansfer the FGD model into mmdet model
python pth_transfer.py --fgd_path $fgd_ckpt --output_path $new_mmdet_ckpt

Test

#single GPU
python tools/test.py configs/retinanet/retinanet_r50_fpn_2x_coco.py $new_mmdet_ckpt --eval bbox

#multi GPU
bash tools/dist_test.sh configs/retinanet/retinanet_r50_fpn_2x_coco.py $new_mmdet_ckpt 8 --eval bbox

Results

Model	Backbone	mAP	config	weight	code
RetinaNet	ResNet-50	40.7	config	baidu	wsfw
RetinaNet	ResNet-101	41.7	config
Faster RCNN	ResNet-50	42.0	config	baidu	dgpf
Faster RCNN	ResNet-101	44.1	config
RepPoints	ResNet-50	42.0	config	baidu	qx5d
RepPoints	ResNet-101	43.8	config
FCOS	ResNet-50	42.7	config	baidu	sedt
MaskRCNN	ResNet-50	42.1	config	baidu	sv8m

Acknowledgement

Our code is based on the project MMDetection.

Thanks to the work GCNet and mmetection-distiller.

Focal and Global Knowledge Distillation for Detectors

Related tags

Overview

FGD

Install MMDetection and MS COCO2017

Add and Replace the codes

Train

Transfer

Test

Results

Acknowledgement

Owner

Mesopotamia

Official implementation of "Dynamic Anchor Learning for Arbitrary-Oriented Object Detection" (AAAI2021).

A Next Generation ConvNet by FaceBookResearch Implementation in PyTorch(Original) and TensorFlow.

Code and Resources for the Transformer Encoder Reasoning Network (TERN)

The official implementation of NeurIPS 2021 paper: Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Edison AT is software Depression Assistant personal.

PyTorch implementation of "A Simple Baseline for Low-Budget Active Learning".

FridaHookAppTool - Frida Hook App Tool With Python

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

An Easy-to-use, Modular and Prolongable package of deep-learning based Named Entity Recognition Models.

Source code and dataset for ACL2021 paper: "ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning".

Confidence Propagation Cluster aims to replace NMS-based methods as a better box fusion framework in 2D/3D Object detection

Code for paper "Document-Level Argument Extraction by Conditional Generation". NAACL 21'

Numerical Methods with Python, Numpy and Matplotlib

Hyperopt for solving CIFAR-100 with a convolutional neural network (CNN) built with Keras and TensorFlow, GPU backend

(CVPR2021) Kaleido-BERT: Vision-Language Pre-training on Fashion Domain

This codebase proposes modular light python and pytorch implementations of several LiDAR Odometry methods

Code for the paper "There is no Double-Descent in Random Forests"

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs, ICCV 2021

[CVPR 2022 Oral] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation