Evaluating Synthetic Skin Lesion Images for Classifier Training: A Safety-Aware Algorithm
cs.CV, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/Amixdu/synth-curator
Terminology
Sources
- Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray images
- Understanding intermediate layers using linear classifier probes
- Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
- Billion-scale similarity search with GPUs
- Analyzing and Improving the Training Dynamics of Diffusion Models
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- Improved Precision and Recall Metric for Assessing Generative Models
- A Non-Parametric Test to Detect Data-Copying in Generative Models
- DINOv2: Learning Robust Visual Features without Supervision
- SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis
- Classification Accuracy Score for Conditional Generative Models
- Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs