Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis
cs.CV, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/A-Abedi/CAT_CKD
Terminology
Sources
- Distilling the Knowledge in a Neural Network
- Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
- FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers
- Supervised Contrastive Learning
- Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
- FEED: Feature-level Ensemble for Knowledge Distillation
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