Comments (6)
Actually I haven't get any gain for now. The result on face detection task of using default setting (alpha=0.25, gamma=2) is just similar with that of using sigmoid_cross_entropy_loss
. I'm still trying to make it work.
from focal-loss.
@ScienceFans I've implement focal loss for SSD object detection framework. In my case, it's worsen than OHEM, but my friend get higher precision using it in semantic segmentation.
The author used it in object detection with a self-created network similar to SSD. Although the performance is amazing, it is contributed by both larger input size and more anchor boxes.
It's doubtful why they did not prove its effectiveness with a prevailed pipeline, and most likely the problem is in implementation details. Hope to see your further update and discussion.
from focal-loss.
@Johnson-yue @XiaoyanLi1
Hi all, in my experiments, focal loss works well on object proposal task. On coco minival
, it performs 2% better than softmax loss (recall=82.53%->84.71% @ 300 proposals, IoU=0.5), in which resnet-101 is used as RPN backbone.
from focal-loss.
@ScienceFans
Hi,your method is faster rcnn or ssd? rpn network and rcnn network use focal loss?
from focal-loss.
@XiaoyanLi1 I also tried focal loss with SSD, it's worse than OHEM.Do you have any update?
from focal-loss.
@bailvwangzi The mAP under the best setting I've tried is still lower than OHEM. Considering the computation cost, I've stopped my experiment. The only conclusion is that the ratio (lambda) between classification loss and regression loss is important. Hyper-parameters I've tried are
- lambda=1, gamma=2
- lambda=4, gamma=2
- lambda=4, gamma=2. alpha=0.25 (best)
from focal-loss.
Related Issues (17)
- FocalLossForwardGPU has unrecognized token HOT 2
- Is this also feasible for segmentation? HOT 1
- When gamma set below 1, loss will go to nan HOT 2
- the normalization is weird
- Some question about the focal_loss_layer.cpp HOT 1
- How to replace FocalLoss in testing phase?
- error LNK2001
- please help! HOT 7
- focal_loss_layer.cpp:43] Check failed: bottom[0]->count() == bottom[1]->count() (8 vs. 4) SIGMOID_CROSS_ENTROPY_LOSS layer inputs must have the same count.
- softmax based version for multiclass case HOT 5
- Have you tested on any dataset? HOT 16
- Seems incorrect use of alpha HOT 1
- Can you provide evaluate result on coco as the paper shows? HOT 2
- prototext files HOT 1
- some questions HOT 1
- SIGABRT error HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from focal-loss.