search

facebookresearch / CutLER

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"
Other
913 stars 90 forks source link

Can I achieve more fine-grained segmentation? #35

Closed loopyli closed 1 year ago

loopyli commented 1 year ago

Can I achieve more fine-grained segmentation? For example, dividing the parts of an object.Thanks for your reply.

frank-xwang commented 1 year ago

Yes, certainly. To obtain more fine-grained segmentation masks, you can consider applying the normalized cut algorithm to the initial masks. This algorithm can help to provide more fine-grained results.

Alternatively, you can also explore using k-Means clustering or spectral clustering methods to obtain more part segmentation masks. These clustering techniques can help further partition the objects into smaller regions or parts, allowing for a more comprehensive and detailed segmentation of the objects in the image.

frank-xwang commented 1 year ago

Closing it now. Please feel free to reopen it if you have further questions.