The paper investigates how many normal samples are required to reliably set an alarm threshold for few‑shot anomaly detectors, focusing on distribution‑free certification limits. Using a frozen DINOv2 PCA residual ranker on 15 MVTec and 12 VisA categories, the authors show that simple leave‑one‑image‑out calibration is limited by resolution and shift, leading to empirical false‑alarm rates far above the nominal level. They derive a category‑count feasibility calculus, demonstrating that at least 14, 29, and 59 independent category draws are needed for 95% upper confidence bounds at α=0.20, 0.10, and 0.05, and propose the CRESS protocol to split source categories into reference, proposal, and certification roles.
whyItMatters":"The study provides concrete numerical thresholds for the amount of source evidence needed to guarantee reliable anomaly detection in new categories, informing practical deployment of few‑shot detectors."
By Gia Huy Thai, Nguyen Thai Anh
arXiv:2608. 15090v1 Announce Type: cross Abstract: Studies of industrial visual inspection commonly report the area under the receiver operating characteristic curve (AUROC) and the overlap between anomaly maps and defect masks.
By Jie Deng
arXiv:2606. 15153v1 Announce Type: new Abstract: Selective prediction with distribution-free risk control promises that, with confidence 1-delta over the calibration draw, the error rate of accepted inputs stays below a user budget alpha.
By Jingwen Zhou, Mingzhe Wang
The paper introduces a framework for auditing image editors that can satisfy regional plausibility constraints while lacking a single latent explanation for the entire output. It defines a common witness grade and witness nerve to formalize local-to-global failures, separating auditing from causal identification. Using Helly-type arguments and a blocker-hypergraph formula, the authors provide short incompatibility certificates, sharp partial-identification bounds for specified image features, and finite-sample outer coverage of identified intervals, validated through controlled MNIST, Morpho-MNIST, and smallNORB experiments.
By Usef Faghihi, Amir Saki
The paper introduces Audit-First VAPO, a method that separates directional admission from magnitude control for selective updates under imperfect verification. It employs an observation-only accept‑appeal‑abstain policy with a finite secondary‑verification budget, freezing the action trace before clean labels are added, and uses finite‑sample bounds to certify harmful risk, coverage, and verifier‑call rate. Experiments on Qwen3.5‑0.8B and GSM8K show that RC‑VAPO achieves high accuracy while maintaining low selected harmful risk and modest verifier cost compared to baseline methods.
By Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Rui Chen, Daren Zha
arXiv:2610.00111v1 Announce Type: new
Abstract: Model judges now supervise multimodal systems at scale, filtering training data, selecting outputs, and supplying the reward that shapes multimodal rea...
By Rasul Khanbayov, Hasan Kurban
arXiv:2607. 19442v1 Announce Type: cross Abstract: Machine unlearning is commonly evaluated by matching a retrained oracle on trained probes.
By Sen Yang, Yuen-Hei Yeung
arXiv:2610.41199v1 Announce Type: new
Abstract: Cameras and vision sensors are widely used for product and process inspection in manufacturing environments. Traditionally, this process required thous...
By Fadel M. Megahed, Ying-Ju Chen
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
The study evaluates 16 AI‑generated image detection methods in a zero‑shot setting, testing 23 pretrained variants on 12 datasets with 2.6 million images from 291 generators. Results show no single detector consistently outperforms others, with accuracy ranging from 37.5 % to 75.0 %. The study highlights that training data alignment and generator type significantly affect performance, especially against modern commercial models, and identifies systematic failure patterns across datasets.
By Simiao Ren (Neo), Yuchen Zhou (Neo), Xingyu Shen (Neo), Kidus Zewde (Neo), Tommy Duong (Neo), George Huang (Neo), Hatsanai (Neo), Tiangratanakul (Dennis), Tsang (Dennis), Ng (Dennis), En Wei, Jiayu Xue
The paper introduces a training‑free, human‑in‑the‑loop anomaly detection framework that allows a domain expert to correct a PatchCore detector by editing its memory bank, without retraining or using gradients. Using only ten golden samples, operator corrections close a median 66% of the performance gap to a fully trained bank, improving 12 of 15 MVTec AD categories while harming none. The approach is evaluated with a rigorous held‑out protocol and shows that passive and active querying yield statistically indistinguishable gains, with a defect‑memory extension failing decisively.
By Ayusha Abbas, Saram Abbas, Kabita Adhikari
The paper introduces a decision‑aware evaluation protocol for medical image segmentation uncertainty that separates uncertainty estimation from deferral policy and assesses their joint performance under fixed review budgets. It reports metrics such as fixed‑budget error reduction, risk‑coverage behavior, region‑level review proxies, structural failure modes, and sensitivity to review assumptions. Experiments on retinal vessel, skin lesion, and polyp segmentation with various backbones and uncertainty estimators show that estimator rankings vary with review unit, uncertainty target, and cost model, and that boundary and thin‑structure failures are partly due to annotation ambiguity.
By Saket Maganti, Shreyank N Gowda