赞
踩
Paddle官方教程: 《AI快车道PaddleDetection – 课节4: 闪电版目标检测算法PP-PicoDet》
PicoDet增强版官方介绍: 超强目标检测算法矩阵(PicoDet-XS)
PicoDet论文: PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
关键点视频也需要学习一下;
论文阅读笔记:《PicoDet论文译读笔记》
模型类型: Anchor-Free
关于PicoDet的整体描述,我觉得可以参照VFNet论文对这类模型的介绍:
[VFNet Paper]: Another type of anchor-free detectors are similar to anchor-based one-stage methods, but they remove the usage of anchor boxes. Instead, they classify each point on the feature pyramids [25_FPN] into foreground classes or background, and directly predict the distances from the foreground point to the four sides of the ground-truth bounding box, to produce the detection. Popular methods include DenseBox [26_DenseBox], FASF [27_FASF], FoveaBox [15_FoveaBox], FCOS [9_FCOS], and SPAD [28_SPAD].
技术一览表:
名称 | cfg |
---|---|
参数初始化 | KaimingNormal |
Loss | l o s s v f l + 2 ⋅ l o s s g i o u + 0.25 ⋅ l o s s d f l loss_{vfl}+2\cdot loss_{giou} + 0.25\cdot loss_{dfl} lossvfl+2⋅lossgiou+0.25⋅lossdfl |
首先,来看看loss函数的整体公式:
l
o
s
s
=
l
o
s
s
v
f
l
+
2
⋅
l
o
s
s
g
i
o
u
+
0.25
⋅
l
o
s
s
d
f
l
loss = loss_{vfl}+2\cdot loss_{giou} + 0.25\cdot loss_{dfl}
loss=lossvfl+2⋅lossgiou+0.25⋅lossdfl
其中,
l
o
s
s
v
f
l
loss_{vfl}
lossvfl:Varifocal Loss。
l
o
s
s
g
i
o
u
loss_{giou}
lossgiou:GIoU Loss。
l
o
s
s
d
f
l
loss_{dfl}
lossdfl:Distribution Focal Loss。
Varifocal Loss是在VarifocalNet[paper]中提出的;
(关于VarifocalNet论文,请参见《【CVPR 2021】VarifocalNet: An IoU-aware Dense Object Detector的译读笔记》)
请参考《mmdetection最小复刻版(十六):iou感知VarifocalNet深入分析》;
用来回归边界框的坐标值;
Distribution Focal Loss出自论文《Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection》;
参考资料:
DFLoss代码实现:
我看了一下PaddleDetection的实现跟MMDetection的实现几乎是一样的;
训练命令:
python tools/train.py -c configs/model/model_coco.yml
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。