| Submission name | 3rd stage | ||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Submission time (UTC) | Sept. 27, 2023, 4:49 p.m. | ||||||||||||||||||||||||||
| User | felix.stillger | ||||||||||||||||||||||||||
| Task | 2D segmentation of unseen objects | ||||||||||||||||||||||||||
| Dataset | TUD-L | ||||||||||||||||||||||||||
| Description | |||||||||||||||||||||||||||
| Evaluation scores |
|
| User | felix.stillger |
|---|---|
| Publication | |
| Implementation | |
| Training image modalities | RGB |
| Test image modalities | RGB |
| Description | Training: There is no training step. Onboarding: For each object, 43 random pre-rendered images from the "train_pbr" dataset are selected. The masks of these objects are then extracted and encoded using CLIP. This data is input into a simple expert binary classifier, trained for each object. Test: During testing, Fastsam-s extracts masks from a test image, and the object's ID is determined by the expert binary classifiers. |
| Computer specifications | RTX 3090, AMD Ryzen 9 3900X 12-Core Processor |