wolfworld6 / feature_intertwiner Goto Github PK

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]

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)

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.

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.

This is probably the most concerned part for most audience.

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}
}