From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation

• URL: http://arxiv.org/abs/2512.13953v1
• Date: Mon, 15 Dec 2025 23:15:36 GMT
• Title: From Unlearning to UNBRANDING: A Benchmark for Trademark-Safe Text-to-Image Generation
• Authors: Dawid Malarz, Artur Kasymov, Filip Manjak, Maciej Zięba, Przemysław Spurek,
• Abstract summary: Brand recognition is multi-dimensional, extending beyond explicit logos to encompass distinctive structural features.<n>We introduce unbranding, a novel task for the fine-grained removal of both trademarks and subtle structural brand features.<n>Our results, validated by our Vision Language Models metric, confirm unbranding is a distinct, practically relevant problem.
• Score: 0.7798283447125206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid progress of text-to-image diffusion models raises significant concerns regarding the unauthorized reproduction of trademarked content. While prior work targets general concepts (e.g., styles, celebrities), it fails to address specific brand identifiers. Crucially, we note that brand recognition is multi-dimensional, extending beyond explicit logos to encompass distinctive structural features (e.g., a car's front grille). To tackle this, we introduce unbranding, a novel task for the fine-grained removal of both trademarks and subtle structural brand features, while preserving semantic coherence. To facilitate research, we construct a comprehensive benchmark dataset. Recognizing that existing brand detectors are limited to logos and fail to capture abstract trade dress (e.g., the shape of a Coca-Cola bottle), we introduce a novel evaluation metric based on Vision Language Models (VLMs). This VLM-based metric uses a question-answering framework to probe images for both explicit logos and implicit, holistic brand characteristics. Furthermore, we observe that as model fidelity increases, with newer systems (SDXL, FLUX) synthesizing brand identifiers more readily than older models (Stable Diffusion), the urgency of the unbranding challenge is starkly highlighted. Our results, validated by our VLM metric, confirm unbranding is a distinct, practically relevant problem requiring specialized techniques. Project Page: https://gmum.github.io/UNBRANDING/.

Related papers

• BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation [64.5799743375449]
  We introduce seamless brand integration in text-to-video (T2V) models.<n>This task confronts three core challenges: maintaining prompt fidelity, ensuring brand recognizability, and achieving contextually natural integration.<n>We propose BrandFusion, a novel multi-agent framework comprising two synergistic phases.
  arXiv  Detail & Related papers  (2026-03-03T10:10:41Z)
• Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition [25.658499211854153]
  We introduce an open-world logo recognition benchmark, a core challenge in product moderation.<n>Unlike traditional logo recognition methods that rely on memorizing representations of tens of thousands of brands, we propose Logo-VGR.<n>We show that Logo-VGR outperforms strong baselines by nearly 10 points in OOD settings.
  arXiv  Detail & Related papers  (2025-09-30T05:35:10Z)
• CIDER: A Causal Cure for Brand-Obsessed Text-to-Image Models [8.256738887166089]
  Text-to-image (T2I) models exhibit a significant yet under-explored "brand bias"<n>We propose CIDER, a model-agnostic framework to mitigate bias at inference-time through prompt refinement to avoid costly retraining.
  arXiv  Detail & Related papers  (2025-09-19T09:30:37Z)
• Seeing the Undefined: Chain-of-Action for Generative Semantic Labels [6.553242735096595]
  We introduce Generative Semantic Labels (GSLs), a novel task that aims to predict a comprehensive set of semantic labels for an image.<n>GSLs generates multiple semantic-level labels, encompassing objects, scenes, attributes, and relationships.<n>We propose Chain-of-Action (CoA), an innovative method designed to tackle the GSLs task.
  arXiv  Detail & Related papers  (2024-11-26T13:09:14Z)
• LogoSticker: Inserting Logos into Diffusion Models for Customized Generation [73.59571559978278]
  We introduce the task of logo insertion into text-to-image models. Our goal is to insert logo identities into diffusion models and enable their seamless synthesis in varied contexts. We present a novel two-phase pipeline LogoSticker to tackle this task.
  arXiv  Detail & Related papers  (2024-07-18T17:54:49Z)
• A Generative Approach for Wikipedia-Scale Visual Entity Recognition [56.55633052479446]
  We address the task of mapping a given query image to one of the 6 million existing entities in Wikipedia. We introduce a novel Generative Entity Recognition framework, which learns to auto-regressively decode a semantic and discriminative code'' identifying the target entity.
  arXiv  Detail & Related papers  (2024-03-04T13:47:30Z)
• Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels [60.675714333081466]
  Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, ie, CLIP, to compensate for insufficient annotations. We advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior.
  arXiv  Detail & Related papers  (2023-03-23T12:39:20Z)
• Label Semantics for Few Shot Named Entity Recognition [68.01364012546402]
  We study the problem of few shot learning for named entity recognition. We leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. Our model learns to match the representations of named entities computed by the first encoder with label representations computed by the second encoder.
  arXiv  Detail & Related papers  (2022-03-16T23:21:05Z)
• Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection [52.36825190893928]
  We propose a novel approach, named Discriminative Semantic Feature Pyramid Network with Guided Anchoring (DSFP-GA) Our approach mainly consists of Discriminative Semantic Feature Pyramid (DSFP) and Guided Anchoring (GA)
  arXiv  Detail & Related papers  (2021-08-31T11:59:00Z)
• The Open Brands Dataset: Unified brand detection and recognition at scale [33.624955564405425]
  "Open Brands" is the largest dataset for brand detection and recognition with rich annotations. "Brand Net" is a network called "Brand Net" to handle brand recognition.
  arXiv  Detail & Related papers  (2020-12-14T09:06:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.