Comments (1)
Hi @yucornetto ,
Thanks for your attention! After the paper release, we made some modifications of K-Net on panoptic segmentation from the original implementation as below:
- In the arxiv v1 version, we use similar annotations as Panoptic FPN, which uses instance segmentation annotations for thing segmentation and use masks generated from panoptic annotations for stuff segmentation. However, when we are implementing Panoptic FPN in MMDet, we find that using panoptic annotations for both things and stuff segmentation yields better results (~1 PQ better). This is because the occlusion is not well handled between masks in the instance segmentation annotations. Therefore, we change to only use panoptic annotation in the new K-Net based on the newest version of MMDetection. This improves ~1.4 PQ of K-Net.
- We fixed a bug in inference. We find a class ID bug when pasting things and stuff masks in arxiv v1 and fixed it when we change to use the COCOPanopticDataset in the newest MMDetection. Simply fixing this issue could improve about 1.0 PQ.
- We tried a new inference strategy. In arxiv v1 we paste masks of things and stuff separately following the same way as Panoptic FPN. In rebuttal, we tried a new strategy that pastes them in a mixed order based on their classification scores. It consistently improves K-Net by 0.3~0.4 PQ.
from k-net.
Related Issues (20)
- inference and visualisation of panoptic knet results HOT 2
- The link of trained model on coco instance segmentation is unaccessible, can you fix it? HOT 1
- KeyError: 'KNet is not in the models registry' when runing 'train.py' HOT 2
- About your semantic segmentation? HOT 1
- ModuleNotFoundError: No module named 'knet' HOT 3
- Implementation about kernel activation HOT 1
- 如何訓練自己的數據集
- About experiments setting HOT 1
- Training on custom dataset HOT 1
- Pre-trained Model
- how to calculate FPS HOT 1
- 'MaskPseudoSampler is already registered in bbox_sampler' HOT 5
- Logs for ADE20K
- the segm mAp result is zero
- OOM error when training on Cityscapes HOT 1
- 使用knet_s3_r50_fpn_1x_coco.py训练
- Can you provide the pre-trained models?
- An error occurred during training
- Welcome update to OpenMMLab 2.0 HOT 1
- About training dataset
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from k-net.