Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ko, Junseok, Kim, Jungwoo, Lee, Jong-Seok
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917531137081344
author Ko, Junseok
Kim, Jungwoo
Lee, Jong-Seok
author_facet Ko, Junseok
Kim, Jungwoo
Lee, Jong-Seok
contents Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a single target concept per image, a limitation increasingly exposed by modern flow-based T2I models, which can generate complex scenes with multiple concepts simultaneously. To address this gap, we introduce compositional multi-concept erasure, a new task that aims to simultaneously remove multiple target concepts within a single scene. We propose CoME-Bench, a benchmark for evaluating compositional multi-concept erasure, which covers both intra- and cross-category scenarios. We further propose Mosaic, a novel framework for multi-concept erasure in flow-based T2I models, which exploits the spatial locality of target concepts in the vector field by dynamically constructing concept-specific masks and selectively blending them without additional optimization. Extensive experiments demonstrate that Mosaic effectively removes multiple target concepts in complex compositional scenes while preserving non-target contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25574
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
Ko, Junseok
Kim, Jungwoo
Lee, Jong-Seok
Computer Vision and Pattern Recognition
Artificial Intelligence
Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a single target concept per image, a limitation increasingly exposed by modern flow-based T2I models, which can generate complex scenes with multiple concepts simultaneously. To address this gap, we introduce compositional multi-concept erasure, a new task that aims to simultaneously remove multiple target concepts within a single scene. We propose CoME-Bench, a benchmark for evaluating compositional multi-concept erasure, which covers both intra- and cross-category scenarios. We further propose Mosaic, a novel framework for multi-concept erasure in flow-based T2I models, which exploits the spatial locality of target concepts in the vector field by dynamically constructing concept-specific masks and selectively blending them without additional optimization. Extensive experiments demonstrate that Mosaic effectively removes multiple target concepts in complex compositional scenes while preserving non-target contexts.
title Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.25574