| Architecture | Softmax, RPN, CARAFE, Convolution, Dense Connections, FPN, ResNet, RoIAlign |
|---|---|
| lr sched | 1x |
| SHOW MORE |
[ALGORITHM]
We provide config files to reproduce the object detection & instance segmentation results in the ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures.
@inproceedings{Wang_2019_ICCV,
title = {CARAFE: Content-Aware ReAssembly of FEatures},
author = {Wang, Jiaqi and Chen, Kai and Xu, Rui and Liu, Ziwei and Loy, Chen Change and Lin, Dahua},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}
The results on COCO 2017 val is shown in the below table.
| Method | Backbone | Style | Lr schd | Test Proposal Num | Inf time (fps) | Box AP | Mask AP | Config | Download |
|---|---|---|---|---|---|---|---|---|---|
| Faster R-CNN w/ CARAFE | R-50-FPN | pytorch | 1x | 1000 | 16.5 | 38.6 | 38.6 | config | model | log |
| - | - | - | - | 2000 | |||||
| Mask R-CNN w/ CARAFE | R-50-FPN | pytorch | 1x | 1000 | 14.0 | 39.3 | 35.8 | config | model | log |
| - | - | - | - | 2000 |
The CUDA implementation of CARAFE can be find at https://github.com/myownskyW7/CARAFE.
Object Detection
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| COCO minival | Mask R-CNN CARAFE (R-50-FPN, 1x, pytorch) | box AP | 39.3 | # 81 |
| COCO minival | Faster R-CNN CARAFE (R-50-FPN, 1x, pytorch) | box AP | 38.6 | # 88 |
Instance Segmentation
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| COCO minival | Faster R-CNN CARAFE (R-50-FPN, 1x, pytorch) | mask AP | 38.6 | # 22 |
| COCO minival | Mask R-CNN CARAFE (R-50-FPN, 1x, pytorch) | mask AP | 35.8 | # 48 |
