The configuration of eval code for differenct scenes

[ChengZY]

I tested on 3D-OVS data. It can achieve similar results (IoU) on the sofa scene.
But the performance for other scenes are not good as expeted.

I noted the language feature images are well-trained, the reason should be the setting of the eval code, such as threshold and the kernal size. Does it mean we need to try the setting manually to achieve the best results?

Below is the sample of the bench scene, including language feature image, groundtruth and the predicted mask. Do you have any suggestion?

[ChengZY]

The predicted language feature image is the 512 dim language picture. To visualize the result, I selected 3 channels as RGB.