Official Implementation of DE-DETR and DELA-DETR in "Towards Data-Efficient Detection Transformers"

Overview

DE-DETRs

By Wen Wang, Jing Zhang, Yang Cao, Yongliang Shen, and Dacheng Tao

This repository is an official implementation of DE-DETR and DELA-DETR in the paper Towards Data-Efficient Detection Transformers.

For the implementation of DE-CondDETR and DELA-CondDETR, please refer to DE-CondDETR.

Introduction

TL; DR. We identify the data-hungry issue of existing detection transformers and alleviate it by simply alternating how key and value sequences are constructed in the cross-attention layer, with minimum modifications to the original models. Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.

DE-DETR

Abstract. Detection Transformers have achieved competitive performance on the sample-rich COCO dataset. However, we show most of them suffer from significant performance drops on small-size datasets, like Cityscapes. In other words, the detection transformers are generally data-hungry. To tackle this problem, we empirically analyze the factors that affect data efficiency, through a step-by-step transition from a data-efficient RCNN variant to the representative DETR. The empirical results suggest that sparse feature sampling from local image areas holds the key. Based on this observation, we alleviate the data-hungry issue of existing detection transformers by simply alternating how key and value sequences are constructed in the cross-attention layer, with minimum modifications to the original models. Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency. Experiments show that our method can be readily applied to different detection transformers and improve their performance on both small-size and sample-rich datasets.

Label Augmentation

Main Results

The experimental results and model weights trained on Cityscapes are shown below.

Model Epochs mAP [email protected] [email protected] [email protected] [email protected] [email protected] Log & Model
DETR 300 11.7 26.5 9.3 2.6 9.2 25.6 Google Drive
DE-DETR 50 22.2 41.7 20.5 4.9 19.7 40.8 Google Drive
DELA-DETR 50 25.2 46.8 22.8 6.5 23.8 44.3 Google Drive

The experimental results and model weights trained on COCO 2017 are shown below.

Model Epochs mAP [email protected] [email protected] [email protected] [email protected] [email protected] Log & Model
DETR 50 33.6 54.6 34.2 13.2 35.7 53.5 Google Drive
DE-DETR 50 40.2 60.4 43.2 23.3 42.1 56.4 Google Drive
DELA-DETR 50 41.9 62.6 44.8 24.9 44.9 56.8 Google Drive

Note:

  1. The number of queries is increased from 100 to 300 in DELA-DETR.
  2. The performance of the model weights on Cityscapes is slightly different from that reported in the paper, because the results in the paper are the average of five repeated runs with different random seeds.

Installation

Requirements

  • Linux, CUDA>=9.2, GCC>=5.4

  • Python>=3.7

  • PyTorch>=1.5.0, torchvision>=0.6.0 (following instructions here)

  • Detectron2>=0.5 for RoIAlign (following instructions here)

  • Other requirements

    pip install -r requirements.txt

Usage

Dataset preparation

The COCO 2017 dataset can be downloaded from here and the Cityscapes datasets can be downloaded from here. The annotations in COCO format can be obtained from here. Afterward, please organize the datasets and annotations as following:

data
└─ cityscapes
   └─ leftImg8bit
      |─ train
      └─ val
└─ coco
   |─ annotations
   |─ train2017
   └─ val2017
└─ CocoFormatAnnos
   |─ cityscapes_train_cocostyle.json
   |─ cityscapes_val_cocostyle.json
   |─ instances_train2017_sample11828.json
   |─ instances_train2017_sample5914.json
   |─ instances_train2017_sample2365.json
   └─ instances_train2017_sample1182.json

The annotations for down-sampled COCO 2017 dataset is generated using utils/downsample_coco.py

Training

Training DELA-DETR on Cityscapes

python -m torch.distributed.launch --nproc_per_node=2 --master_port=29501 --use_env main.py --dataset_file cityscapes --coco_path data/cityscapes --batch_size 4 --model dela-detr --repeat_label 2 --nms --num_queries 300 --wandb

Training DELA-DETR on down-sampled COCO 2017, with e.g. sample_rate=0.01

python -m torch.distributed.launch --nproc_per_node=2 --master_port=29501 --use_env main.py --dataset_file cocodown --coco_path data/coco --sample_rate 0.01 --batch_size 4 --model dela-detr --repeat_label 2 --nms --num_queries 300 --wandb

Training DELA-DETR on COCO 2017

python -m torch.distributed.launch --nproc_per_node=8 --master_port=29501 --use_env main.py --dataset_file coco --coco_path data/coco --batch_size 4 --model dela-detr --repeat_label 2 --nms --num_queries 300 --wandb

Training DE-DETR on Cityscapes

python -m torch.distributed.launch --nproc_per_node=2 --master_port=29501 --use_env main.py --dataset_file cityscapes --coco_path data/cityscapes --batch_size 4 --model de-detr --wandb

Training DETR baseline

Please refer to the detr branch.

Evaluation

You can get the pretrained model (the link is in "Main Results" session), then run following command to evaluate it on the validation set:

<training command> --resume <path to pre-trained model> --eval

Acknowledgement

This project is based on DETR and Deformable DETR. Thanks for their wonderful works. See LICENSE for more details.

Citing DE-DETRs

If you find DE-DETRs useful in your research, please consider citing:

@misc{wang2022towards,
      title={Towards Data-Efficient Detection Transformers}, 
      author={Wen Wang and Jing Zhang and Yang Cao and Yongliang Shen and Dacheng Tao},
      year={2022},
      eprint={2203.09507},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
Owner
Wen Wang
Wen Wang
Graph neural network message passing reframed as a Transformer with local attention

Adjacent Attention Network An implementation of a simple transformer that is equivalent to graph neural network where the message passing is done with

Phil Wang 49 Dec 28, 2022
Activity image-based video retrieval

Cross-modal-retrieval Our approach is focus on Activity Image-to-Video Retrieval (AIVR) task. The compared methods are state-of-the-art single modalit

BCMI 75 Oct 21, 2021
PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

Learning to Generate Grounded Visual Captions without Localization Supervision This is the PyTorch implementation of our paper: Learning to Generate G

Chih-Yao Ma 41 Nov 17, 2022
Official Pytorch Implementation for Splicing ViT Features for Semantic Appearance Transfer presenting Splice

Splicing ViT Features for Semantic Appearance Transfer [Project Page] Splice is a method for semantic appearance transfer, as described in Splicing Vi

Omer Bar Tal 253 Jan 06, 2023
Hyper-parameter optimization for sklearn

hyperopt-sklearn Hyperopt-sklearn is Hyperopt-based model selection among machine learning algorithms in scikit-learn. See how to use hyperopt-sklearn

1.4k Jan 01, 2023
Codes for “A Deeply Supervised Attention Metric-Based Network and an Open Aerial Image Dataset for Remote Sensing Change Detection”

DSAMNet The pytorch implementation for "A Deeply-supervised Attention Metric-based Network and an Open Aerial Image Dataset for Remote Sensing Change

Mengxi Liu 41 Dec 14, 2022
CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

CDGAN CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation CDGAN Implementation in PyTorch This is the imple

Kancharagunta Kishan Babu 6 Apr 19, 2022
Python scripts for performing stereo depth estimation using the HITNET Tensorflow model.

HITNET-Stereo-Depth-estimation Python scripts for performing stereo depth estimation using the HITNET Tensorflow model from Google Research. Stereo de

Ibai Gorordo 76 Jan 02, 2023
Official PyTorch implementation of Spatial Dependency Networks.

Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling Đorđe Miladinović   Aleksandar Stanić   Stefan Bauer   Jürgen Schmid

Djordje Miladinovic 34 Jan 19, 2022
FAMIE is a comprehensive and efficient active learning (AL) toolkit for multilingual information extraction (IE)

FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction

18 Sep 01, 2022
NovelD: A Simple yet Effective Exploration Criterion

NovelD: A Simple yet Effective Exploration Criterion Intro This is an implementation of the method proposed in NovelD: A Simple yet Effective Explorat

29 Dec 05, 2022
Spatial Sparse Convolution Library

SpConv: Spatially Sparse Convolution Library PyPI Install Downloads CPU (Linux Only) pip install spconv CUDA 10.2 pip install spconv-cu102 CUDA 11.1 p

Yan Yan 1.2k Jan 07, 2023
Pytorch modules for paralel models with same architecture. Ideal for multi agent-based systems

WideLinears Pytorch parallel Neural Networks A package of pytorch modules for fast paralellization of separate deep neural networks. Ideal for agent-b

1 Dec 17, 2021
Pytorch code for our paper "Feedback Network for Image Super-Resolution" (CVPR2019)

Feedback Network for Image Super-Resolution [arXiv] [CVF] [Poster] Update: Our proposed Gated Multiple Feedback Network (GMFN) will appear in BMVC2019

Zhen Li 539 Jan 06, 2023
CLOOB training (JAX) and inference (JAX and PyTorch)

cloob-training Pretrained models There are two pretrained CLOOB models in this repo at the moment, a 16 epoch and a 32 epoch ViT-B/16 checkpoint train

Katherine Crowson 64 Nov 27, 2022
DANA paper supplementary materials

DANA Supplements This repository stores the data, results, and R scripts to generate these reuslts and figures for the corresponding paper Depth Norma

0 Dec 17, 2021
a pytorch implementation of auto-punctuation learned character by character

Learning Auto-Punctuation by Reading Engadget Articles Link to Other of my work 🌟 Deep Learning Notes: A collection of my notes going from basic mult

Ge Yang 137 Nov 09, 2022
Semi-automated OpenVINO benchmark_app with variable parameters

Semi-automated OpenVINO benchmark_app with variable parameters. User can specify multiple options for any parameters in the benchmark_app and the progam runs the benchmark with all combinations of gi

Yasunori Shimura 8 Apr 11, 2022
Official Pytorch implementation of 'GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network' (NeurIPS 2020)

Official implementation of GOCor This is the official implementation of our paper : GOCor: Bringing Globally Optimized Correspondence Volumes into You

Prune Truong 71 Nov 18, 2022
Progressive Coordinate Transforms for Monocular 3D Object Detection

Progressive Coordinate Transforms for Monocular 3D Object Detection This repository is the official implementation of PCT. Introduction In this paper,

58 Nov 06, 2022