Exposing Text-Image Inconsistency Using Diffusion Models
In the battle against widespread online misinformation, a growing problem is text-image inconsistency, where images are misleadingly paired with texts with different intent or meaning. Existing classification-based methods for text-image inconsistency can identify contextual inconsistencies but fail to provide explainable justifications for their decisions that humans can understand. Although more nuanced, human evaluation is impractical at scale and susceptible to errors. To address these limitations, this study introduces D-TIIL (Diffusion-based Text-Image Inconsistency Localization), which employs text-to-image diffusion models to localize semantic inconsistencies in text and image pairs. These models, trained on large-scale datasets act as ``omniscient" agents that filter out irrelevant information and incorporate background knowledge to identify inconsistencies. In addition, D-TIIL uses text embeddings and modified image regions to visualize these inconsistencies. To evaluate D-TIIL's efficacy, we introduce a new TIIL dataset containing 14K consistent and inconsistent text-image pairs. Unlike existing datasets, TIIL enables assessment at the level of individual words and image regions and is carefully designed to represent various inconsistencies. D-TIIL offers a scalable and evidence-based approach to identifying and localizing text-image inconsistency, providing a robust framework for future research combating misinformation.
Code (1)
Tasks
MisinformationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
Classifier-Free Guidance (CFG) has been widely used in text-to-image diffusion models, where the CFG scale is introduced to control the strength of text guidance on the whole image space. However, we argue that a global …
DenoisingSemantic SegmentationExposing the Fake: Effective Diffusion-Generated Images Detection
Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, ther…
DenoisingImage GenerationPrompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models
The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in gene…
HallucinationImage GenerationKnowledge GraphsText GenerationMV2UV: Generating High-quality UV Texture Maps with Multiview Prompts
Generating high-quality textures for 3D assets is a challenging task. Existing multiview texture generation methods suffer from the multiview inconsistency and missing textures on unseen parts, while UV inpainting textur…
UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person has a different appearance e.g. pose, f…
DisentanglementImage GenerationPose TransferText-to-Image Generation+1