search

CVI-SZU / CLIMS

[CVPR 2022] CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation
MIT License
124 stars 12 forks source link

The difference between previous version with new version. #9

Closed 376498485 closed 1 year ago

376498485 commented 2 years ago

Hi, thanks for your great work. Could you please tell me the difference between previous version with new version？What have you done to improve your miu from 70 to 73？

Sierkinhane commented 2 years ago

Hi, there are three main differences: 1) We didn't fine-tune the CLIP model in the latest implementation. 2) The backbone network including 1x1 convolutional layer was purely initialized from the pre-trained multi-label classification model 'res50_cam.pth'. 3) The CBS Loss. Please check more details in the source code.

If you would like to cite our paper, please cite the performance in the CVPR version. We will update the paper and upload code for COCO in the coming month.

BTW, welcome to star our project！ ：）

Sierkinhane commented 2 years ago

Actually, with SAME DeepLabv2, the performance is boosted from ~69 to ~70 (imagenet pre-trained) and ~70 to 71.4 (coco pretrained).

| CLIMS(camera-ready) | I | DeepLabV2 | ImageNet | 69.3 | 68.7 | | CLIMS(camera-ready) | I | DeepLabV2 | COCO | 70.4 | 70.0 | | CLIMS(this repo) | I | DeepLabV2 |ImageNet | 70.3 | 70.6 | | CLIMS(this repo) | I | DeepLabV2 | COCO | 71.4 | 71.2 |

376498485 commented 2 years ago

Thank you very much! I will follow your next work.