PyTorchKR Papers

최신 논문

총 2편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2607.06094v1cs.LG

Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems

Faults on a cyber-physical system (CPS) are too rare and unrepresentative to characterise, or even to select a model on, so detection must instead model normal behaviour; the standard point-adjusted evaluation, however, rewards detectors that never do. CPS normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes rather than a single blob; we state this structure as ten assumptions (A1-A10), abbreviated Massive, Implicit, Imbalanced Multimodality (MIIM). We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering, scored in the latent rather than by a global density or a reconstruction residual, and evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration. On three real CPS datasets (WADI, HAI, SKAB), the detector wins both the combined column and the difficult correlation/dynamics-fault column on all three, reaching difficult-subset AUROC 0.831 on HAI, 0.726 on WADI, and 0.610 on SKAB. The margin is largest on the two multimodal datasets the MIIM assumptions target and slimmest on the near-unimodal one, tracking multimodality as the thesis predicts, and it holds against three deep detectors (USAD, TranAD, GDN) re-computed with the same raw metrics, all of which collapse on the difficult subset. The methodological contributions are the MIIM assumption set, the difficulty-stratified fair protocol, and a latent-only score that drops reconstruction because a flexible decoder rebuilds the hard faults faithfully.

arXiv:2412.08949v4cs.CV공식 코드 · Papers with Code

튜닝된 역방향 지식 증류: 크로스모달 튜너를 활용한 멀티모달 산업 이상 탐지 향상

Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal Tuners

멀티모달 산업 이상 탐지에서 기존 지식 증류(KD) 기반 방법들이 융합된 특징으로 교사 표현을 생성할 때 단일 모달리티에만 존재하는 이상을 포착하지 못하는 문제를 해결하기 위해, 각 모달리티에 독립 브랜치를 할당하는 Multi-branch 설계와 Crossmodal Filter·Amplifier로 구성된 Crossmodal Tuner를 도입한 Tuned Reverse Distillation(TRD)을 제안한다. MVTec-3D AD, Eyecandies 등 멀티모달 AD 데이터셋 실험에서 기존 최첨단 방법 대비 우수한 이상 탐지 및 위치 추정 성능을 달성함을 검증하였다.