-
Dear Authors,
We are conducting a study to evaluate Video Self-Supervised models holistically and would like to include your EVEREST model too. Can you please share the Kinetics-400 pretrained VIT-B …
-
hi , thanks your great work
can you share with us
1. supervised learning or self-supervised learning?
2. how to prepare the data?
thank you
-
Hi, I found in one literature review that they categorised your model as "Self-supervised generative", but in your article as I understood, you are using labels during pre-training (so basically the s…
-
## Audio SSL
SSL的思想可以抽象为让模型学习对应的数据的内在空间结构和表达,SSL在audio上的效果要差于NLP和CV,这体现在:
1. 现实生活中音频的不确定性,比如人与人之间、甚至是个人的不同时期,不同情绪下说话的差异,气息、声调都有区别,录音设备的不同和摆放方式也会导致数据的差异,这使得SSL较难学到声音的潜在结构;
2. 不同噪声对音频的叠加干扰,会扭曲SSL学习…
-
我在Code中好像没发现Self-Supervised的代码,有劳您能提供一下吗,十分感谢。
Could u upload code of self-supervised to represent embedding.Thanks.
-
In normal self-supervised learning, pretraining is usually achieved reconstruct the data with masking. However, in your implementation, pertaining is achieved by predicting the task with masked input.…
-
I have compared the instance retrieval performance of my current model vs. dinov2 and my model training on my data performs better than dinov2, although it does quite well. But it looks like the way d…
-
Could you please advise on how to change the backbone of the SimSiam example to ViT? (https://docs.lightly.ai/self-supervised-learning/tutorials/package/tutorial_simsiam_esa.html)
Additionally, for…
-
The goal of this issue is to track new self-supervised methods and to which extent they are implemented in Lightly.
See also our [#papers channel](https://discord.com/channels/752876370337726585/81…
-
Hi, amazingwork!
I noticed that in the paper you use self-supervised weights, but I ran into problems when trying to reproduce the results.
specifically, I directly change 'vit_base_patch16_224_in…