-
我在寻找一种可以解决以下问题的方法:
因为人失误造成的错标,或者说模棱两可的数据标成任意一个类都可以,这样产生的数据集本身存在问题。
可是我的分类任务可能差异性并不是很明显,属于细颗粒度的分类,不像狗和茶杯这样的类别,而是OK和NG这样的判定,可能稍微有一点裂缝没啥问题,裂缝太大才有问题,稍微有一点缺失没问题,缺失很大才有问题,您的这个方法可以应用在我这个任务上吗?像我这种二分类是不是使用…
-
Now that the fields of semi-supervised and self-supervised learning are becoming more and more important, I wish to cover an example showing how to train GANs for semi-supervised image classification …
-
I am using UniMatch for domain adaptation according to your above suggestions as mentioned in #55 . But I am facing problems and errors.
1. As you said we should cutmix labeled data (source domain)…
-
### Describe the bug
Real text output looks like:
```
It's hard to say who is smarter between Isaac Newton and Albert Einstein, as both were incredibly intelligent individuals with unique perspe…
-
In the inference, if the score is lower than stale_best_score, then the label be replaced with the label from this JSON file. How is this JSON file obtained? I also found out that without using this J…
-
hello, @rxtan2
In your paper, I found you use 5 conditions to get the best result in the Polyvore dataset. Can you explain what conditions you used? Because I see in UT-Zappos50K, it has gender, cla…
-
Hi Young, great work!
I was wondering if this method can perform well for the Domain Adaptation task. I have a dataset (street driving domain) that is unlabelled and would like to include it in the…
-
Thanks for sharing great work and dataset!
I have two questions about paper.
First of all, I think that authors mainly follow the losses and architecture of ALBEF. But, CTP do not use the ITM loss…
-
Hi,
Thanks very much for your work.
I wonder how should I modify your loss to adapting to the case of multiple positive samples per query.
For example, query.shape = (1,128), positive_keys.shape =…
-
## Background
- ODQA 서베이 논문 요약: [Retrieving and Reading : A Comprehensive Survey on Open-domain Question Answering (2021)](https://arxiv.org/pdf/2101.00774.pdf)
- 추후에 나온 모델보다 성능이 낮다고 증명된 것은 선이 그어져…