dinov2

dinov2 copied to clipboard

[request] Depth estimation documentation, training code and / or model weights

37

Related issues: - #6 - #14 - #46 - #97

patricklabatut

Related issues: - #1 - #2 - #15 - #48

patricklabatut

Hi, In Table 9: Evaluation of frozen features on instance-level recognition. of the table, it shows the performance for OpenCLIP-G/14 is 50.7 for Oxford-M and 19.7 for Oxford-H. However, we...

strbcks

Feature transformation before PCA

2

Thank you for sharing Figure 1 from the paper, which showcases the mapping of features to RGB channels using PCA. I found it to be really impressive! I was wondering...

WangYixuan12

How to evaluate on image retrieval datasets using nearest neighbors?

1

How to evaluate the model on image retrieval datasets such as Oxford-H? Thanks a lot!

KeyaoZhao

- Fixed type errors found by the `mypy`. - Sorted imports with `isort`. - Removed unused args in the `_get_entries_path`, `_get_class_ids_path`, `_get_class_names_path` - Added missed requirements (`PLW`, which gets `numpy`,...

leo-gan

need easy shell cmd to analyze one picture

1

This is the function in the official demo. I want to write a piece of python code, then execute a script command, and pass in parameters such as the image...

shblhy

Hi, I tried to reproduce the evaluation numbers in Table 4 and Table 6 of the paper. I downloaded the backbones and linear classifiers from the readme and composed the...

ArneNx

Thanks so much for this inspiring and excellent work! I implemented the patch matching but did not perform as well as the demo on the paper. Could you introduce more...

XinyaChen21

Does patch matching work without iBoT?

3

 Do you still get this type of correspondence without iBoT? I assume patch-level features receive zero supervision signal without iBoT, is this correct?

JunzheJosephZhu