Rex Cheng

You can use the provided interactive tool to create a mask.

The masks should be read by PIL as index masks. See https://github.com/hkchengrex/XMem/blob/main/docs/PALETTE.md

In this mode, we don't care about the class. It doesn't matter that they are in the same class. If you want to track them independently, label them independently. On...

Yes.

The json files allow users to propagate segment information (e.g., object classes) to the output. It is not strictly necessary. Max allocated memory is just reporting the maximum amount of...

I think your mask is an RGB image and not an index mask as mentioned above.

> The masks should be read by PIL as index masks. See https://github.com/hkchengrex/XMem/blob/main/docs/PALETTE.md Please see this reply from above. Simply put, the underlying data structure should be a single-channel integer...

The conversion is wrong. You would need to find the unique colors in the image and remap the pixels. The following is a response from Claude 3 Sonnet. > To...

Two observations: 1. The cropped version is working better 2. The input and output colors don't match It seems to me that your mask input (or conversion) is still buggy.

Thank you for the update. It is possible that having many targets degrades the output (due to increased noise in memory matching), especially in out-of-domain cases like yours.