VisualDeltas: Learning Preferences from Visual Quality Perturbations
We present VisualDeltas, a lightweight preference-learning framework that extracts supervision from visual quality variations in multimodal data. By leveraging the systematic impact of image quality on visual perception and reasoning, VisualDeltas induces informative preference signals without relying on human annotations or external teachers. The framework supports both label-free and label-based regimes, enabling flexible use of available supervision when present. Across diverse multimodal benchmarks and model scales, VisualDeltas consistently outperforms rejection-sampling fine-tuning and improves generalization, and extends naturally to a range of visual degradations.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Image Quality Assessment: From Human to Machine Preference
Image Quality Assessment (IQA) based on human subjective preferences has undergone extensive research in the past decades. However, with the development of communication protocols, the visual data consumption volume of m…
Image Quality AssessmentVisual-Friendly Concept Protection via Selective Adversarial Perturbations
Personalized concept generation by tuning diffusion models with a few images raises potential legal and ethical concerns regarding privacy and intellectual property rights. Researchers attempt to prevent malicious person…
Harmonic Adversarial Attack Method
Adversarial attacks find perturbations that can fool models into misclassifying images. Previous works had successes in generating noisy/edge-rich adversarial perturbations, at the cost of degradation of image quality. S…
Adversarial AttackQuality Assessment for AI Generated Images with Instruction Tuning
Artificial Intelligence Generated Content (AIGC) has grown rapidly in recent years, among which AI-based image generation has gained widespread attention due to its efficient and imaginative image creation ability. Howev…
Image GenerationImage Quality AssessmentPersonalizing Text-to-Image Generation to Individual Taste
Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human appeal, they fail to capture the inherent …
Text-to-Image Generation