Code for our NeurIPS 2021 paper Mining the Benefits of Two-stage and One-stage HOI Detection

Last update: Dec 14, 2022

Related tags

Deep Learning CDN

Overview

CDN

Code for our NeurIPS 2021 paper "Mining the Benefits of Two-stage and One-stage HOI Detection".

Contributed by Aixi Zhang*, Yue Liao*, Si Liu, Miao Lu, Yongliang Wang, Chen Gao and Xiaobo Li.

Installation

Installl the dependencies.

pip install -r requirements.txt

Data preparation

HICO-DET

HICO-DET dataset can be downloaded here. After finishing downloading, unpack the tarball (hico_20160224_det.tar.gz) to the data directory.

Instead of using the original annotations files, we use the annotation files provided by the PPDM authors. The annotation files can be downloaded from here. The downloaded annotation files have to be placed as follows.

data
 └─ hico_20160224_det
     |─ annotations
     |   |─ trainval_hico.json
     |   |─ test_hico.json
     |   └─ corre_hico.npy
     :

V-COCO

First clone the repository of V-COCO from here, and then follow the instruction to generate the file instances_vcoco_all_2014.json. Next, download the prior file prior.pickle from here. Place the files and make directories as follows.

qpic
 |─ data
 │   └─ v-coco
 |       |─ data
 |       |   |─ instances_vcoco_all_2014.json
 |       |   :
 |       |─ prior.pickle
 |       |─ images
 |       |   |─ train2014
 |       |   |   |─ COCO_train2014_000000000009.jpg
 |       |   |   :
 |       |   └─ val2014
 |       |       |─ COCO_val2014_000000000042.jpg
 |       |       :
 |       |─ annotations
 :       :

For our implementation, the annotation file have to be converted to the HOIA format. The conversion can be conducted as follows.

PYTHONPATH=data/v-coco \
        python convert_vcoco_annotations.py \
        --load_path data/v-coco/data \
        --prior_path data/v-coco/prior.pickle \
        --save_path data/v-coco/annotations

Note that only Python2 can be used for this conversion because vsrl_utils.py in the v-coco repository shows a error with Python3.

V-COCO annotations with the HOIA format, corre_vcoco.npy, test_vcoco.json, and trainval_vcoco.json will be generated to annotations directory.

Pre-trained model

Download the pretrained model of DETR detector for ResNet50, and put it to the params directory.

python convert_parameters.py \
        --load_path params/detr-r50-e632da11.pth \
        --save_path params/detr-r50-pre-2stage-q64.pth \
        --num_queries 64

python convert_parameters.py \
        --load_path params/detr-r50-e632da11.pth \
        --save_path params/detr-r50-pre-2stage.pth \
        --dataset vcoco

Training

After the preparation, you can start training with the following commands. The whole training is split into two steps: CDN base model training and dynamic re-weighting training. The trainings of CDN-S for HICO-DET and V-COCO are shown as follows.

HICO-DET

python -m torch.distributed.launch \
        --nproc_per_node=8 \
        --use_env \
        main.py \
        --pretrained params/detr-r50-pre-2stage-q64.pth \
        --output_dir logs \
        --dataset_file hico \
        --hoi_path data/hico_20160224_det \
        --num_obj_classes 80 \
        --num_verb_classes 117 \
        --backbone resnet50 \
        --num_queries 64 \
        --dec_layers_hopd 3 \
        --dec_layers_interaction 3 \
        --epochs 90 \
        --lr_drop 60 \
        --use_nms_filter

python -m torch.distributed.launch \
        --nproc_per_node=8 \
        --use_env \
        main.py \
        --pretrained logs/checkpoint_last.pth \
        --output_dir logs/ \
        --dataset_file hico \
        --hoi_path data/hico_20160224_det \
        --num_obj_classes 80 \
        --num_verb_classes 117 \
        --backbone resnet50 \
        --num_queries 64 \
        --dec_layers_hopd 3 \
        --dec_layers_interaction 3 \
        --epochs 10 \
        --freeze_mode 1 \
        --obj_reweight \
        --verb_reweight \
        --use_nms_filter

V-COCO

python -m torch.distributed.launch \
        --nproc_per_node=8 \
        --use_env \
        main.py \
        --pretrained params/detr-r50-pre-2stage.pth \
        --output_dir logs \
        --dataset_file vcoco \
        --hoi_path data/v-coco \
        --num_obj_classes 81 \
        --num_verb_classes 29 \
        --backbone resnet50 \
        --num_queries 100 \
        --dec_layers_hopd 3 \
        --dec_layers_interaction 3 \
        --epochs 90 \
        --lr_drop 60 \
        --use_nms_filter

python -m torch.distributed.launch \
        --nproc_per_node=8 \
        --use_env \
        main.py \
        --pretrained logs/checkpoint_last.pth \
        --output_dir logs/ \
        --dataset_file vcoco \
        --hoi_path data/v-coco \
        --num_obj_classes 81 \
        --num_verb_classes 29 \
        --backbone resnet50 \
        --num_queries 100 \
        --dec_layers_hopd 3 \
        --dec_layers_interaction 3 \
        --epochs 10 \
        --freeze_mode 1 \
        --verb_reweight \
        --use_nms_filter

Evaluation

HICO-DET

You can conduct the evaluation with trained parameters for HICO-DET as follows.

python -m torch.distributed.launch \
        --nproc_per_node=8 \
        --use_env \
        main.py \
        --pretrained pretrained/hico_cdn_s.pth \
        --dataset_file hico \
        --hoi_path data/hico_20160224_det \
        --num_obj_classes 80 \
        --num_verb_classes 117 \
        --backbone resnet50 \
        --num_queries 64 \
        --dec_layers_hopd 3 \
        --dec_layers_interaction 3 \
        --eval \
        --use_nms_filter

V-COCO

For the official evaluation of V-COCO, a pickle file of detection results have to be generated. You can generate the file and then evaluate it as follows.

python generate_vcoco_official.py \
        --param_path pretrained/vcoco_cdn_s.pth \
        --save_path vcoco.pickle \
        --hoi_path data/v-coco \
        --dec_layers_hopd 3 \
        --dec_layers_interaction 3 \
        --use_nms_filter

cd data/v-coco
python vsrl_eval.py vcoco.pickle

Results

HICO-DET

	Full (D)	Rare (D)	Non-rare (D)	Full(KO)	Rare (KO)	Non-rare (KO)	Download
CDN-S (R50)	31.44	27.39	32.64	34.09	29.63	35.42	model
CDN-B (R50)	31.78	27.55	33.05	34.53	29.73	35.96	model
CDN-L (R101)	32.07	27.19	33.53	34.79	29.48	36.38	model

D: Default, KO: Known object

V-COCO

	Scenario 1	Scenario 2	Download
CDN-S (R50)	61.68	63.77	model
CDN-B (R50)	62.29	64.42	model
CDN-L (R101)	63.91	65.89	model

Citation

Please consider citing our paper if it helps your research.

@article{zhang2021mining,
  title={Mining the Benefits of Two-stage and One-stage HOI Detection},
  author={Zhang, Aixi and Liao, Yue and Liu, Si and Lu, Miao and Wang, Yongliang and Gao, Chen and Li, Xiaobo},
  journal={arXiv preprint arXiv:2108.05077},
  year={2021}
}

License

CDN is released under the MIT license. See LICENSE for additional details.

Acknowledge

Some of the codes are built upon PPDM, DETR and QPIC. Thanks them for their great works!

Code for our NeurIPS 2021 paper Mining the Benefits of Two-stage and One-stage HOI Detection

Related tags

Overview

CDN

Installation

Data preparation

HICO-DET

V-COCO

Pre-trained model

Training

HICO-DET

V-COCO

Evaluation

HICO-DET

V-COCO

Results

HICO-DET

V-COCO

Citation

License

Acknowledge

Owner

An efficient 3D semantic segmentation framework for Urban-scale point clouds like SensatUrban, Campus3D, etc.

Code for paper 'Hand-Object Contact Consistency Reasoning for Human Grasps Generation' at ICCV 2021

NeROIC: Neural Object Capture and Rendering from Online Image Collections

Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.

Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction

QA-GNN: Question Answering using Language Models and Knowledge Graphs

Final term project for Bayesian Machine Learning Lecture (XAI-623)

Paper Code：A Self-adaptive Weighted Differential Evolution Approach for Large-scale Feature Selection

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

Haze Removal can remove slight to extreme cases of haze affecting an image

Replication Code for "Self-Supervised Bug Detection and Repair" NeurIPS 2021

TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection

A study project using the AA-RMVSNet to reconstruct buildings from multiple images

Certifiable Outlier-Robust Geometric Perception

Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation

Yolov5-opencv-cpp-python - Example of using ultralytics YOLO V5 with OpenCV 4.5.4, C++ and Python

GeneDisco is a benchmark suite for evaluating active learning algorithms for experimental design in drug discovery.

This is a Deep Leaning API for classifying emotions from human face and human audios.

Sibur challange 2021 competition - 6 place