HOME CHALLENGES DATASETS TASKS LEADERBOARDS SUBMIT RESULTS Sign in

Submission: ocdit/TUD-L/run:0_tudl_ens:11

Download submission
Submission name run:0_tudl_ens:11
Submission time (UTC) Oct. 17, 2025, 12:21 p.m.
User mulmer
Task Model-based 2D segmentation of unseen objects
Dataset TUD-L
Description
Evaluation scores
AP:0.522
AP50:0.915
AP75:0.523
AP_large:0.562
AP_medium:0.514
AP_small:0.427
AR1:0.555
AR10:0.556
AR100:0.556
AR_large:0.603
AR_medium:0.540
AR_small:0.425
average_time_per_image:0.000

Method: ocdit

User mulmer
Publication Ulmer, Maximilian, et al. "Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation.", ICCV 2025
Implementation https://github.com/DLR-RM/oc-dit
Training image modalities RGB
Test image modalities RGB
Description
Computer specifications