Skip to content
Codebase of the paper "Feature Intertwiner for Object Detection", ICLR 2019
Python C Cuda C++ Other
Branch: master
Clone or download
Latest commit 2aafd3d Apr 28, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
assets tiny Mar 28, 2019
configs codebase init Mar 28, 2019
datasets codebase init Mar 28, 2019
lib codebase init Mar 28, 2019
script codebase init Mar 28, 2019
tools codebase init Mar 28, 2019
.gitignore tiny Mar 28, 2019
INSTALL.md codebase init Mar 28, 2019
LICENSE
README.md fix readme bug Apr 28, 2019
main.py codebase init Mar 28, 2019
setup.sh codebase init Mar 28, 2019

README.md

Feature Intertwiner for Object Detection

A PyTorch implementation of our paper published at ICLR 2019.

By Hongyang Li, Bo Dai, Shaoshuai Shi, Wanli Ouyang, and Xiaogang Wang.

Paper: [arXiv] [Openreview]

A 50-min talk presented at GTC 2019: [GTC Video] [GTC Slides]

Overview

Our assumption is that semantic features for one category should be the same as shown in (a) below. Due to the inferior up-sampling design in RoI operation, shown in (b), the reliable set (green) could guide the feature learning of the less reliable set (blue).

Here comes the proposed feature intertwiner:

  • PyTorch 0.3
  • Code/framework based on Mask-RCNN.
  • Datasets: COCO and Pascal VOC (not in this repo)

How to run

Follow instructions in INSTALL.md to set up datasets, symlinks, compilation, etc.

To train, sh script/base_4gpu 105/meta_105_quick_1 0,2,5,7 # gpu ids or:

simply execute python main.py. The configurations are stored in the configs folder.

To test, change the flag --phase in main.py to inference.

Performance

Object detection single-model performance (bounding box AP) on the COCO test-dev. The InterNet multi-scale is achieved with data augmentation, 1.5× longer training time and multi-scale training. Our InterNet is also a two-stage detector.

methods backbone AP AP_50 AP_75 AP_small AP_medium AP_large
YOLOv2 DarkNet-19 21.6 44.0 19.2 5.0 22.4 35.5
SSD513 ResNet-101-SSD 31.2 50.4 33.3 10.2 34.5 49.8
R-FCN ResNet-101 29.9 51.9 - 10.8 32.8 45.0
Mask-RCNN ResNet-101-FPN 38.2 60.3 41.7 20.1 41.1 50.2
InterNet ResNet-101-FPN 42.5 65.1 49.4 25.4 46.6 54.3
InterNet multi-scale ResNet-101-FPN 44.2 67.5 51.1 27.2 50.3 57.7

Adapting Feature Intertwiner to your own task

This is probably the most concerned part for most audience.

Citation

Please cite in the following manner if you find it useful in your research:

@inproceedings{li2019_internet,
  title = {{Feature Intertwiner for Object Detection}},
  author = {Hongyang Li and Bo Dai and Shaoshuai Shi and Wanli Ouyanbg and Xiaogang Wang},
  booktitle = {ICLR},
  year = {2019}
}
You can’t perform that action at this time.