Unverified50% confidenceFactExact time
Flownomaly, in a frozen DINOv2 feature space, learns a velocity field through conditional flow matching to pull query tokens back toward their normal counterparts, and uses the squared residual before and after restoration as the anomaly signal.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFlownomaly performs conditional transport on frozen DINOv2 features, with the restoration target anchored to normal support samples, structurally reducing the risk of anomalous content being reproduced.79% similarUnverifiedFrozen DINOv2 features mean that Flownomaly's detection ceiling is constrained by the sensitivity of that feature space to fine-grained defects.75% similarUnverified直接用冻结的 DINOv2 全局特征跑 k-NN 是对其最不公平的评估方式，因为测试的是未经调整的嵌入空间几何结构64% similarUnverifiedREMORY faces a token drift risk: once the data distribution shifts, performance degrades, requiring periodic fine-tuning of the encoder and monitoring of the exact match rate.63% similarUnverified冻结基准可能因数据泄露被纳入模型训练数据而随时间失去区分力，这是一个权衡63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098071API
curl https://kongchang.com/api/v1/knowledge/claims/1098071MCP
get_claim(id=1098071)