Genμ Challenge (U&ME Workshop @ ICCV'2025)

Baselines

The following table presents the baseline scores for existing unlearning methods: ESD,CA and FMN proposed by Gandikota et.al (2023), Kumari et.al (2023) and Zhang et.al (2023) respectively across various concepts, evaluated using ERR Score and L2 Norm metrics.

Concept	Type	ESD		CA		FMN
		ERR Score	L2 Norm	ERR Score	L2 Norm	ERR Score	L2 Norm
Barbeton Daisy	Object	0.507	0.465	0.493	0.456	0.492	0.473
Apple Fruit	Object	0.472	0.493	0.417	0.455	0.494	0.472
Golf Ball	Object	0.431	0.529	0.502	0.468	0.474	0.487
Blue Jay	Animal	0.509	0.464	0.493	0.475	0.461	0.477
Welsh Springer Spaniel	Animal	0.489	0.479	0.501	0.472	0.472	0.489
Van Gogh	Style	0.432	0.528	0.524	0.453	0.496	0.475
Doodle	Style	0.476	0.491	0.498	0.471	0.469	0.329
Neon	Style	0.487	0.481	0.492	0.473	0.464	0.464
Monet	Style	0.511	0.463	0.524	0.453	0.498	0.468
Sketch	Style	0.484	0.483	0.509	0.464	0.481	0.482
Wedding	Scene	0.479	0.487	0.466	0.503	0.472	0.411
Sunset	Scene	0.397	0.459	0.416	0.444	0.431	0.473
Rainfall	Scene	0.443	0.519	0.417	0.543	0.467	0.494
Aurora Borialis	Scene	0.487	0.481	0.382	0.575	0.442	0.518
Scenerie	Scene	0.497	0.473	0.428	0.531	0.401	0.558
Sleeping	Action	0.482	0.485	0.475	0.487	0.402	0.509
Walking	Action	0.513	0.462	0.485	0.479	0.367	0.591
Eating	Action	0.463	0.501	0.473	0.495	0.413	0.546
Dancing	Action	0.432	0.528	0.451	0.441	0.433	0.516
Jumping	Action	0.496	0.474	0.417	0.443	0.402	0.498