Learned about the dichotomous image segmentation task.
The following link gives a demo about it:DIS Background Removal – a Hugging Face Space by doevent
汤浩楠 のすべての投稿
週報(TANG)
review wentian’s paper
doing experiment on DIS5k dataset
週報(TANG)
finish experiment about RGBD mirror segementation
IOU:0.7376;
Emeasure: 0.853;
Smeasure 0.839;
Fmeasure 0.821;
MAE: 0.043. BER:0.0843
週報(TANG)
Reading papers
Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation
SegFix: Model-Agnostic Boundary Refinement for Segmentation
Real-Time High-Resolution Background Matting
Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
Progressive Semantic Segmentation
週報(TANG)
11.19
I am revising my paper.
- More results compared with SOTA methods are added.
2. Give some examples of DIS5K datasets.
11.20
learning how to use Docker
11.21
Improving the first draft of the patent
11.22
Organize experimental results and code files related to Boundary-aware DIS. Upload to Gitlab.
WEEKLY REVIEW
I’m in the process of revising my paper based on the review comments.
The following experimental results are being supplemented with the evaluation metric BDE, which is a measure of the quality of the boundary of the segmentation result
週報(TANG)
- Completed a first draft of a patent
- Learned to use git
- Learning the usage of C# and .NET in progress
- Completed a course report on Advanced Robotic Vision.
週報(TANG)
I am learning .NET MAUI and want to design a cross-platform AI assistant.