Res2Net for Instance segmentation and Object detection using MaskRCNN

Overview

Res2Net for Instance segmentation and Object detection using MaskRCNN

Since the MaskRCNN-benchmark of facebook is deprecated, we suggest to use our mmdetection based res2net for object detection and instance segmentation to get the SOTA performance on both two tasks. https://github.com/Res2Net/mmdetection

Update

  • 2020.3.10 The mmdetection based implementation of object detection and instance segmentation using Res2Net_v1b has the SOTA performance. We have released our code on: https://github.com/Res2Net/mmdetection. Our Res2Net_v1b achieves a considerable performance gain on mmdetection compared with existing backbone models.

Introduction

This repo uses MaskRCNN as the baseline method for Instance segmentation and Object detection. We use the maskrcnn-benchmark as the baseline.

Res2Net is a powerful backbone architecture that can be easily implemented into state-of-the-art models by replacing the bottleneck with Res2Net module. More detail can be found on "Res2Net: A New Multi-scale Backbone Architecture" and our project page .

Performance

Results on Instance segmentation and Object detection using MaskRCNN.

Performance on Instance segmentation:

Backbone Setting AP AP50 AP75 APs APm APl
ResNet-50 64w 33.9 55.2 36.0 14.8 36.0 50.9
ResNet-50 48w×2s 34.2 55.6 36.3 14.9 36.8 50.9
Res2Net-50 26w×4s 35.6 57.6 37.6 15.7 37.9 53.7
Res2Net-50 18w×6s 35.7 57.5 38.1 15.4 38.1 53.7
Res2Net-50 14w×8s 35.3 57.0 37.5 15.6 37.5 53.4
ResNet-101 64w 35.5 57.0 37.9 16.0 38.2 52.9
Res2Net-101 26w×4s 37.1 59.4 39.4 16.6 40.0 55.6

Performance on Object detection:

Backbone Setting AP AP50 AP75 APs APm APl
ResNet-50 64w 37.5 58.4 40.3 20.6 40.1 49.7
ResNet-50 48w×2s 38.0 58.9 41.3 20.5 41.0 49.9
Res2Net-50 26w×4s 39.6 60.9 43.1 22.0 42.3 52.8
Res2Net-50 18w×6s 39.9 60.9 43.3 21.8 42.8 53.7
Res2Net-50 14w×8s 39.1 60.2 42.1 21.7 41.7 52.8
ResNet-101 64w 39.6 60.6 43.2 22.0 43.2 52.4
Res2Net-101 26w×4s 41.8 62.6 45.6 23.4 45.5 55.6

(Noted that pretrained models trained with pytorch usually achieve slightly worse performance than the caffe pretrained models, we took advice from the author of MaskRCNN-benchmark to use 2x schedule in all experiments including baseline and our method.)

Applications

Other applications such as Classification, Semantic segmentation, pose estimation, Class activation map can be found on https://mmcheng.net/res2net/ and https://github.com/gasvn/Res2Net .

Installation

(This repo is based on the mask-rcnn benchmark, the useage is remain the same with the original repo.)

Check INSTALL.md for installation instructions.

Perform training on COCO dataset

For the following examples to work, you need to first install maskrcnn_benchmark.

You will also need to download the COCO dataset. We recommend to symlink the path to the coco dataset to datasets/ as follows

We use minival and valminusminival sets from Detectron

# symlink the coco dataset
cd ~/github/maskrcnn-benchmark
mkdir -p datasets/coco
ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
ln -s /path_to_coco_dataset/train2014 datasets/coco/train2014
ln -s /path_to_coco_dataset/test2014 datasets/coco/test2014
ln -s /path_to_coco_dataset/val2014 datasets/coco/val2014
# or use COCO 2017 version
ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
ln -s /path_to_coco_dataset/train2017 datasets/coco/train2017
ln -s /path_to_coco_dataset/test2017 datasets/coco/test2017
ln -s /path_to_coco_dataset/val2017 datasets/coco/val2017

# for pascal voc dataset:
ln -s /path_to_VOCdevkit_dir datasets/voc

P.S. COCO_2017_train = COCO_2014_train + valminusminival , COCO_2017_val = minival

You can also configure your own paths to the datasets. For that, all you need to do is to modify maskrcnn_benchmark/config/paths_catalog.py to point to the location where your dataset is stored. You can also create a new paths_catalog.py file which implements the same two classes, and pass it as a config argument PATHS_CATALOG during training.

Single GPU training

Most of the configuration files that we provide assume that we are running on 8 GPUs. In order to be able to run it on fewer GPUs, there are a few possibilities:

1. Run the following without modifications

python /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "/path/to/config/file.yaml"

This should work out of the box and is very similar to what we should do for multi-GPU training. But the drawback is that it will use much more GPU memory. The reason is that we set in the configuration files a global batch size that is divided over the number of GPUs. So if we only have a single GPU, this means that the batch size for that GPU will be 8x larger, which might lead to out-of-memory errors.

If you have a lot of memory available, this is the easiest solution.

2. Modify the cfg parameters

If you experience out-of-memory errors, you can reduce the global batch size. But this means that you'll also need to change the learning rate, the number of iterations and the learning rate schedule.

Here is an example for Mask R-CNN Res2Net-50 FPN with the 2x schedule:

python tools/train_net.py --config-file "configs/pytorch_mask_rcnn_R2_50_s4_FPN_2x.yaml" SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025 SOLVER.MAX_ITER 720000 SOLVER.STEPS "(480000, 640000)" TEST.IMS_PER_BATCH 1

This follows the scheduling rules from Detectron. Note that we have multiplied the number of iterations by 8x (as well as the learning rate schedules), and we have divided the learning rate by 8x.

We also changed the batch size during testing, but that is generally not necessary because testing requires much less memory than training.

Multi-GPU training

We use internally torch.distributed.launch in order to launch multi-gpu training. This utility function from PyTorch spawns as many Python processes as the number of GPUs we want to use, and each Python process will only use a single GPU.

export NGPUS=8
python -m torch.distributed.launch --nproc_per_node=$NGPUS /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "configs/pytorch_mask_rcnn_R2_50_s4_FPN_2x.yaml"

Inference in a few lines

We provide a helper class to simplify writing inference pipelines using pre-trained models. Here is how we would do it. Run this from the demo folder:

from maskrcnn_benchmark.config import cfg
from predictor import COCODemo

config_file = "../configs/pytorch_mask_rcnn_R2_50_s4_FPN_2x.yaml"

# update the config options with the config file
cfg.merge_from_file(config_file)
# manual override some options
cfg.merge_from_list(["MODEL.DEVICE", "cpu"])

coco_demo = COCODemo(
    cfg,
    min_image_size=800,
    confidence_threshold=0.7,
)
# load image and then run prediction
image = ...
predictions = coco_demo.run_on_opencv_image(image)

Adding your own dataset

This implementation adds support for COCO-style datasets. But adding support for training on a new dataset can be done as follows:

from maskrcnn_benchmark.structures.bounding_box import BoxList

class MyDataset(object):
    def __init__(self, ...):
        # as you would do normally

    def __getitem__(self, idx):
        # load the image as a PIL Image
        image = ...

        # load the bounding boxes as a list of list of boxes
        # in this case, for illustrative purposes, we use
        # x1, y1, x2, y2 order.
        boxes = [[0, 0, 10, 10], [10, 20, 50, 50]]
        # and labels
        labels = torch.tensor([10, 20])

        # create a BoxList from the boxes
        boxlist = BoxList(boxes, image.size, mode="xyxy")
        # add the labels to the boxlist
        boxlist.add_field("labels", labels)

        if self.transforms:
            image, boxlist = self.transforms(image, boxlist)

        # return the image, the boxlist and the idx in your dataset
        return image, boxlist, idx

    def get_img_info(self, idx):
        # get img_height and img_width. This is used if
        # we want to split the batches according to the aspect ratio
        # of the image, as it can be more efficient than loading the
        # image from disk
        return {"height": img_height, "width": img_width}

That's it. You can also add extra fields to the boxlist, such as segmentation masks (using structures.segmentation_mask.SegmentationMask), or even your own instance type.

For a full example of how the COCODataset is implemented, check maskrcnn_benchmark/data/datasets/coco.py.

Citation

If you find this work or code is helpful in your research, please cite:

@article{gao2019res2net,
  title={Res2Net: A New Multi-scale Backbone Architecture},
  author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
  journal={IEEE TPAMI},
  year={2020},
  doi={10.1109/TPAMI.2019.2938758}, 
}
@misc{massa2018mrcnn,
author = {Massa, Francisco and Girshick, Ross},
title = {{maskrnn-benchmark: Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch}},
year = {2018},
howpublished = {\url{https://github.com/facebookresearch/maskrcnn-benchmark}},
note = {Accessed: [Insert date here]}
}

Acknowledge

This code is partly borrowed from maskrcnn-benchmark. maskrcnn-benchmark is released under the MIT license. See LICENSE for additional details.

Owner
Res2Net Applications
Applications of the multi-scale backbone Res2Net (TPAMI 2020)
Res2Net Applications
Official implementation of Densely connected normalizing flows

Densely connected normalizing flows This repository is the official implementation of NeurIPS 2021 paper Densely connected normalizing flows. Poster a

Matej Grcić 31 Dec 12, 2022
Multi-Anchor Active Domain Adaptation for Semantic Segmentation (ICCV 2021 Oral)

Multi-Anchor Active Domain Adaptation for Semantic Segmentation Munan Ning*, Donghuan Lu*, Dong Wei†, Cheng Bian, Chenglang Yuan, Shuang Yu, Kai Ma, Y

Munan Ning 36 Dec 07, 2022
StyleSwin: Transformer-based GAN for High-resolution Image Generation

StyleSwin This repo is the official implementation of "StyleSwin: Transformer-based GAN for High-resolution Image Generation". By Bowen Zhang, Shuyang

Microsoft 349 Dec 28, 2022
Official repository for the CVPR 2021 paper "Learning Feature Aggregation for Deep 3D Morphable Models"

Deep3DMM Official repository for the CVPR 2021 paper Learning Feature Aggregation for Deep 3D Morphable Models. Requirements This code is tested on Py

38 Dec 27, 2022
implicit displacement field

Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields [project page][paper][cite] Geometry-Consistent Neural Shape Represe

Yifan Wang 100 Dec 19, 2022
Few-shot Neural Architecture Search

One-shot Neural Architecture Search uses a single supernet to approximate the performance each architecture. However, this performance estimation is super inaccurate because of co-adaption among oper

Yiyang Zhao 38 Oct 18, 2022
Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

PSML paper: Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors PSML_IONE,PSML_ABNE,PSML_DEEPLINK,PSML_SNNA: numpy

13 Nov 27, 2022
CAUSE: Causality from AttribUtions on Sequence of Events

CAUSE: Causality from AttribUtions on Sequence of Events

Wei Zhang 21 Dec 01, 2022
Pytorch Implementation for CVPR2018 Paper: Learning to Compare: Relation Network for Few-Shot Learning

LearningToCompare Pytorch Implementation for Paper: Learning to Compare: Relation Network for Few-Shot Learning Howto download mini-imagenet and make

Jackie Loong 246 Dec 19, 2022
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

Under-exposure introduces a series of visual degradation, i.e. decreased visibility, intensive noise, and biased color, etc. To address these problems, we propose a novel semi-supervised learning app

Yang Wenhan 117 Jan 03, 2023
Official PyTorch Implementation of Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition, ICCV 2021

Official PyTorch Implementation of Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition, ICCV 2021

26 Dec 07, 2022
(AAAI2022) Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation

SM-PPM This is a Pytorch implementation of our paper "Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Seman

W-zx-Y 10 Dec 07, 2022
Code, environments, and scripts for the paper: "How Private Is Your RL Policy? An Inverse RL Based Analysis Framework"

Privacy-Aware Inverse RL (PRIL) Analysis Framework Code, environments, and scripts for the paper: "How Private Is Your RL Policy? An Inverse RL Based

1 Dec 06, 2021
TrackFormer: Multi-Object Tracking with Transformers

TrackFormer: Multi-Object Tracking with Transformers This repository provides the official implementation of the TrackFormer: Multi-Object Tracking wi

Tim Meinhardt 321 Dec 29, 2022
Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation

SSWS-loss_function_based_on_MS-TCN Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation Supervised Sliding Window

3 Aug 03, 2022
InsightFace: 2D and 3D Face Analysis Project on MXNet and PyTorch

InsightFace: 2D and 3D Face Analysis Project on MXNet and PyTorch

Deep Insight 13.2k Jan 06, 2023
This repository is for our EMNLP 2021 paper "Automated Generation of Accurate & Fluent Medical X-ray Reports"

Introduction: X-Ray Report Generation This repository is for our EMNLP 2021 paper "Automated Generation of Accurate & Fluent Medical X-ray Reports". O

no name 36 Dec 16, 2022
Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds

Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds Xinxin Zuo, Sen Wang, Minglun Gong, Li Cheng Prerequisites We have tested the code on Ubun

41 Dec 12, 2022
Active window border replacement for window managers.

xborder Active window border replacement for window managers. Usage git clone https://github.com/deter0/xborder cd xborder chmod +x xborders ./xborder

deter 250 Dec 30, 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