-
- https://arxiv.org/abs/2104.03602
- 2021
自己教師付き学習法は、近年、教師付き学習との差を縮めることに成功したことから、コンピュータビジョンの分野でますます注目を集めています。
自然言語処理(NLP)では、自己教師付き学習と変換器はすでに選択されている手法です。
最近の文献によると、トランスフォーマーはコンピュータビジョンでも人気が高まっている…
e4exp updated
3 years ago
-
link: https://arxiv.org/abs/1910.11664
-
I tried to reproduce the self-supervised training by pase+ on librispeech 100h training dataset. I'm just wondering, for contamination part, what is the downsample filter (downsample_irfiles in cfg fi…
-
Hello,
I'm experiencing challenges
training the model on a custom dataset consisting of medical images.
Environment & Setup:
GPUs: 8 x A100 40GB
Batch Size: 32 per GPU (Total: 256)
Learni…
-
@yaringal
Thank you for your example, it helps a lot to understand the paper. I am currently use the proposed formula (exp(-log_var)*loss+log_var)) in self-supervised learning with uncertainty…
-
I would like to ask whether it is possible to train the model transferred from self-supervision through mmdet. Is the naming of the backbone consistent with most self-supervised models?
-
Hello, I would like to ask why I don't find the decoder section inside the mod of the code, is there no decoder? And I see that the paper is written with self-supervision inside, may I ask if this pap…
-
[Self-Supervised Sparse-to-Dense: Self-Supervised Depth Completion from LiDAR and Monocular Camera](https://ieeexplore.ieee.org/abstract/document/8793637)
-
Hi, thank you for open-sourcing the code, really liked the idea of the paper.
Just wondering if you tried to optimize the projection matrix based on proximity in the descriptor space instead of sup…
-
Since Self Supervised learning is still a fairly new concept, a lot of people don't have an understanding of it.
What if we add an "Introduction to SSL" or Get started section for SSL?
This wi…