Submission: lcc-fastsam/ITODD/4th. stage

Download submission
Submission name 4th. stage
Submission time (UTC) Sept. 28, 2023, 3:34 a.m.
User felix.stillger
Task Model-based 2D segmentation of unseen objects
Dataset ITODD
Description
Evaluation scores
AP:0.041
AP50:0.076
AP75:0.042
AP_large:0.044
AP_medium:0.017
AP_small:-1.000
AR1:0.025
AR10:0.073
AR100:0.081
AR_large:0.080
AR_medium:0.059
AR_small:-1.000
average_time_per_image:1.244

Method: lcc-fastsam

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