Unverified50% confidenceFactExact time
The core assumption of the transfer map is that the feature shift from the source scanner to the target scanner is approximately a structured transformation at the global level, which can be learned from paired samples
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSlideRuler first learns a transfer map using paired repeat scans, and at inference time calibrates only a single scan, keeping the foundation model parameters unchanged throughout the process73% similarVerifiedTransfer learning refers to migrating model parameters pre-trained on large-scale datasets to a specific small-sample task for fine-tuning.73% similarUnverified预训练模型迁移复用的假设是模型在源域学到的特征具有跨域泛化能力，但高层语义特征可能存在显著的域偏移72% similarUnverifiedDuring the inference stage, TRACE retrieves compact evidential prompts from the structure and feeds them to the model as additional information.70% similarUnverifiedInference-time guidance steers sampling trajectories toward regions consistent with observations by adding the gradient of the observation likelihood at each step of reverse diffusion or flow, without requiring model retraining.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/986972API
curl https://kongchang.com/api/v1/knowledge/claims/986972MCP
get_claim(id=986972)