Deep Structured Instance Graph for Distilling Object Detectors (ICCV 2021)

Related tags

Deep LearningDsig
Overview

DSIG

Deep Structured Instance Graph for Distilling Object Detectors

Authors: Yixin Chen, Pengguang Chen, Shu Liu, Liwei Wang, Jiaya Jia.

[pdf] [slide] [supp] [bibtex]

This repo provides the implementation of paper "Deep Structured Instance Graph for Distilling Object Detectors"(Dsig) based on detectron2. Specifically, aiming at solving the feature imbalance problem while further excavating the missing relation inside semantic instances, we design a graph whose nodes correspond to instance proposal-level features and edges represent the relation between nodes. We achieve new state-of-the-art results on the COCO object detection task with diverse student-teacher pairs on both one- and two-stage detectors.

Installation

Requirements

  • Python >= 3.6
  • Pytorch >= 1.7.0
  • Torchvision >= 0.8.1
  • Pycocotools 2.0.2

Follow the install instructions in detectron2, note that in this repo we use detectron2 commit version ff638c931d5999f29c22c1d46a3023e67a5ae6a1. Download COCO dataset and export DETECTRON2_DATASETS=$COCOPATH to direct to COCO dataset. We prepare our pre-trained weights for training in Student-Teacher format, please follow the instructions in Pretrained.

Running

We prepare training configs following the detectron2 format. For training a Faster R-CNN R18-FPN student with a Faster R-CNN R50-FPN teacher on 4 GPUs:

./start_train.sh train projects/Distillation/configs/Distillation-FasterRCNN-R18-R50-dsig-1x.yaml

For testing:

./start_train.sh eval projects/Distillation/configs/Distillation-FasterRCNN-R18-R50-dsig-1x.yaml

For debugging:

./start_train.sh debugtrain projects/Distillation/configs/Distillation-FasterRCNN-R18-R50-dsig-1x.yaml

Results and Models

Faster R-CNN:

Experiment(Student-Teacher) Schedule AP Config Model
R18-R50 1x 37.25 config googledrive
R50-R101 1x 40.57 config googledrive
R101-R152 1x 41.65 config googledrive
MNV2-R50 1x 34.44 config googledrive
EB0-R101 1x 37.74 config googledrive

RetinaNet:

Experiment(Student-Teacher) Schedule AP Config Model
R18-R50 1x 34.72 config googledrive
MNV2-R50 1x 32.16 config googledrive
EB0-R101 1x 34.44 config googledrive

More models and results will be released soon.

Citation

@inproceedings{chen2021dsig,
    title={Deep Structured Instance Graph for Distilling Object Detectors},
    author={Yixin Chen, Pengguang Chen, Shu Liu, Liwei Wang, and Jiaya Jia},
    booktitle={IEEE International Conference on Computer Vision (ICCV)},
    year={2021},
}

Contact

Please contact [email protected].

Owner
DV Lab
Deep Vision Lab
DV Lab
GitHub Repository
[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo Lukas Koestler1*    Nan Yang1,2*,†    Niclas Zeller2,3    Daniel Cremers1

TUM Computer Vision Group 744 Jan 04, 2023
Learning Synthetic Environments and Reward Networks for Reinforcement Learning

Learning Synthetic Environments and Reward Networks for Reinforcement Learning We explore meta-learning agent-agnostic neural Synthetic Environments (

AutoML-Freiburg-Hannover 16 Sep 02, 2022
Simple ONNX operation generator. Simple Operation Generator for ONNX.

sog4onnx Simple ONNX operation generator. Simple Operation Generator for ONNX. https://github.com/PINTO0309/simple-onnx-processing-tools Key concept V

Katsuya Hyodo 6 May 15, 2022
Python package for visualizing the loss landscape of parameterized quantum algorithms.

orqviz A Python package for easily visualizing the loss landscape of Variational Quantum Algorithms by Zapata Computing Inc. orqviz provides a collect

Zapata Computing, Inc. 75 Dec 30, 2022
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency

Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency This is a official implementation of the CycleContrast introduced in

13 Nov 14, 2022
Code release for "Self-Tuning for Data-Efficient Deep Learning" (ICML 2021)

Self-Tuning for Data-Efficient Deep Learning This repository contains the implementation code for paper: Self-Tuning for Data-Efficient Deep Learning

THUML @ Tsinghua University 101 Dec 11, 2022
Python inverse kinematics for your robot model based on Pinocchio.

Python inverse kinematics for your robot model based on Pinocchio.

Stéphane Caron 50 Dec 22, 2022
Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

Continual Reinforcement Learning This repository provides a simple way to run continual reinforcement learning experiments in PyTorch, including evalu

55 Dec 24, 2022
Codes for NeurIPS 2021 paper "On the Equivalence between Neural Network and Support Vector Machine".

On the Equivalence between Neural Network and Support Vector Machine Codes for NeurIPS 2021 paper "On the Equivalence between Neural Network and Suppo

Leslie 8 Oct 25, 2022
HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement

HiFi++ : a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement This is the unofficial implementation of Vocoder part of

Rishikesh (ऋषिकेश) 118 Dec 29, 2022
Objective of the repository is to learn and build machine learning models using Pytorch. 30DaysofML Using Pytorch

30 Days Of Machine Learning Using Pytorch Objective of the repository is to learn and build machine learning models using Pytorch. List of Algorithms

Mayur 119 Nov 24, 2022
Generalized Random Forests

generalized random forests A pluggable package for forest-based statistical estimation and inference. GRF currently provides non-parametric methods fo

GRF Labs 781 Dec 25, 2022
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.

Python library with Neural Networks for Image Segmentation based on Keras and TensorFlow. The main features of this library are: High level API (just

Pavel Yakubovskiy 4.2k Jan 09, 2023
Using image super resolution models with vapoursynth and speeding them up with TensorRT

vs-RealEsrganAnime-tensorrt-docker Using image super resolution models with vapoursynth and speeding them up with TensorRT. Also a docker image since

4 Aug 23, 2022
Efficiently Disentangle Causal Representations

Efficiently Disentangle Causal Representations Install dependency pip install -r requirements.txt Main experiments Causality direction prediction cd

4 Apr 01, 2022
The first dataset of composite images with rationality score indicating whether the object placement in a composite image is reasonable.

Object-Placement-Assessment-Dataset-OPA Object-Placement-Assessment (OPA) is to verify whether a composite image is plausible in terms of the object p

BCMI 53 Nov 15, 2022
LAnguage Model Analysis

LAMA: LAnguage Model Analysis LAMA is a probe for analyzing the factual and commonsense knowledge contained in pretrained language models. The dataset

Meta Research 960 Jan 08, 2023
This toolkit provides codes to download and pre-process the SLUE datasets, train the baseline models, and evaluate SLUE tasks.

slue-toolkit We introduce Spoken Language Understanding Evaluation (SLUE) benchmark. This toolkit provides codes to download and pre-process the SLUE

ASAPP Research 39 Sep 21, 2022
DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency

[CVPR19] DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency (Oral paper) Authors: Kuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang PDF:

Kuang-Jui Hsu 139 Dec 22, 2022
Multiple paper open-source codes of the Microsoft Research Asia DKI group

📫 Paper Code Collection (MSRA DKI Group) This repo hosts multiple open-source codes of the Microsoft Research Asia DKI Group. You could find the corr

Microsoft 249 Jan 08, 2023