jponttuset / mcg

Multiscale Combinatorial Grouping - Object Proposals and Segmentation
http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/
Other
306 stars 139 forks source link

about the segmentation result in paper #22

Open forrestsz opened 4 years ago

forrestsz commented 4 years ago

dear author, I download the BSDSdatasets MCG Proposals in link: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/#results

the file in each mat including:

  1. superpixels:481*321 uint16
  2. scores: 6340*1 double
  3. labels: 6340*1 cell

i have try only using the superpixels for evaluation in BSDS500 benchmark here: https://github.com/BIDS/BSDS500

but i get the result like this GT=0.35, RI=0.77, VI=4.24

in the paper, the report result in page5 table 1 is: SC=0.611, RI=0.813, VI=1.548.

i want to know if correct for my operation, maybe i have some mistakes..

thank for your reply!

jponttuset commented 4 years ago

Dear linqinghong, I am sorry but I cannot give this level of support for MCG anymore. Best,

sunshineatnoon commented 2 years ago

Dear linqinghong, I am sorry but I cannot give this level of support for MCG anymore. Best,

Hi, @jponttuset Could you please elaborate how to get the object proposal from the downloaded results? I'm having a hard time to figure out how to parse the label (63401 double) and score (63401 cell) domain in the downloaded results. Specifically, I'd like to get the object proposals shown in the last column of Fig.2 in the paper for the BSDS dataset. Thanks!