Block Selection Method for Using Feature Norm in Out-of-distribution Detection

2022-12-05 · CVPR 2023 1 · Yeonguk Yu, Sungho Shin, Seongju Lee, Changhyun Jun, Kyoobin Lee

Detecting out-of-distribution (OOD) inputs during the inference stage is crucial for deploying neural networks in the real world. Previous methods commonly relied on the output of a network derived from the highly activated feature map. In this study, we first revealed that a norm of the feature map obtained from the other block than the last block can be a better indicator of OOD detection. Motivated by this, we propose a simple framework consisting of FeatureNorm: a norm of the feature map and NormRatio: a ratio of FeatureNorm for ID and OOD to measure the OOD detection performance of each block. In particular, to select the block that provides the largest difference between FeatureNorm of ID and FeatureNorm of OOD, we create Jigsaw puzzle images as pseudo OOD from ID training samples and calculate NormRatio, and the block with the largest value is selected. After the suitable block is selected, OOD detection with the FeatureNorm outperforms other OOD detection methods by reducing FPR95 by up to 52.77% on CIFAR10 benchmark and by up to 48.53% on ImageNet benchmark. We demonstrate that our framework can generalize to various architectures and the importance of block selection, which can improve previous OOD detection methods as well.

📄 PDF Abstract BibTeX arXiv:2212.02295

Code (1)

gist-ailab/block-selection-for-ood-detection 공식 구현 pytorch

Tasks

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Jigsaw Jigsaw is a self-supervision approach that relies on jigsaw-like puzzles as the pretext task in order to learn image representations.

End-to-end Hyperspectral Image Change Detection Network Based on Band Selection

2023-07-23 · Qingren Yao, Yuan Zhou, Chang Tang, Wei Xiang

For hyperspectral image change detection (HSI-CD), one key challenge is to reduce band redundancy, as only a few bands are crucial for change detection while other bands may be adverse to it. However, most existing HSI-C…

Change Detection

Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos

2022-03-25 · Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, Seung-Ik Lee

Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous eve…

Anomaly Detection Clustering Representation Learning Supervised Anomaly Detection+1

Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows

2024-02-09 · Evan D. Cook, Marc-Antoine Lavoie, Steven L. Waslander

Out-of-distribution (OOD) detection is a critical task for safe deployment of learning systems in the open world setting. In this work, we investigate the use of feature density estimation via normalizing flows for OOD d…

Density Estimation image-classification Image Classification Out-of-Distribution Detection+1

Capturing the security expert knowledge in feature selection for web application attack detection

2024-07-26 · Amanda Riverol, Gustavo Betarte, Rodrigo Martínez, Álvaro Pardo

This article puts forward the use of mutual information values to replicate the expertise of security professionals in selecting features for detecting web attacks. The goal is to enhance the effectiveness of web applica…

Blocking feature selection

Omni-AD: Learning to Reconstruct Global and Local Features for Multi-class Anomaly Detection

2025-03-27 · Jiajie Quan, Ao Tong, Yuxuan Cai, Xinwei He 외

In multi-class unsupervised anomaly detection(MUAD), reconstruction-based methods learn to map input images to normal patterns to identify anomalous pixels. However, this strategy easily falls into the well-known "learni…

Anomaly Detection Decoder Multi-class Anomaly Detection Unsupervised Anomaly Detection