-
## Background
- swin base 모델로만 앙상블을 해본 결과, LB 점수가 0.005~0.01 정도밖에 오르질 않았음. (pspnet, upernet, PAN)
- 백본의 다양성을 높이면 앙상블 효과를 더 끌어올릴 수 있을 것 같음.
## Content
- hrnet + ocr (mmseg). epoch 50
- valid…
-
Is it correct for me to understand this way?
You are implementing kmeans on stm32, through kmeans, the data received by the sensor is divided into several categories and labeled, and after a certain …
-
您好，我注意到在论文中当λI=0时，可以使用image-text数据进行训练。我目前的数据集只有image和label，没有bouding box，能同样以这样的方式进行微调吗，应该怎么做呢？…
-
I am confused by the implementation of pseudo-labelling in this library ([lib/algs/pseudo_label.py](lib/algs/pseudo_label.py)). Especially, the forward() has:
```
y_probs = y.softmax(1)
onehot_la…
-
## Please select if your request is either something new or an enhancement ##
- [ ] Enhancement of an existing Feature.
- [x] Request of a new feature.
## Please select the area your reques…
-
This is an RFC for the implementation of a multithreaded version of the connected component labeling algorithm.
Such algorithms have appeared in research papers since a few years ago. A common theme…
-
Hi im new to this field and i have a minor question about TRZSL setting.
At first, I thought that in TRZSL, only images corresponding to unseen classes could be accessed during training. But after re…
-
Thanks for the great work on debiasing pseudo-labeling!
Regarding Eqn(5), it is mentioned in the paper that [R(1)] adaptive margin loss can demand a larger margin between hardly biased and highly b…
-
Hi,
Thanks for the interesting work and sharing the code.
Recently, I reproduced the Fine-Tuning baseline method based on the released code for Self-Tuning method (directly delete the unlabeled …
-
Hello @AlexeyAB.
I have trained a heavy network (yolov3) and a tiny network (tiny_yolov3). How can I connect them to act as a teacher-student network.
Regards!
Clyde