paper-with-me

Papers

Boosting Out-of-distribution Detection with Typical Features

2022-10-09 · Yao Zhu, Yuefeng Chen, Chuanlong Xie, Xiaodan Li, Rong Zhang, Hui Xue, Xiang Tian, Bolun Zheng, Yaowu Chen

Out-of-distribution (OOD) detection is a critical task for ensuring the reliability and safety of deep neural networks in real-world scenarios. Different from most previous OOD detection methods that focus on designing OOD scores or introducing diverse outlier examples to retrain the model, we delve into the obstacle factors in OOD detection from the perspective of typicality and regard the feature's high-probability region of the deep model as the feature's typical set. We propose to rectify the feature into its typical set and calculate the OOD score with the typical features to achieve reliable uncertainty estimation. The feature rectification can be conducted as a {plug-and-play} module with various OOD scores. We evaluate the superiority of our method on both the commonly used benchmark (CIFAR) and the more challenging high-resolution benchmark with large label space (ImageNet). Notably, our approach outperforms state-of-the-art methods by up to 5.11$\%$ in the average FPR95 on the ImageNet benchmark.

📄 PDF Abstract BibTeX arXiv:2210.04200

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Energy-based Hopfield Boosting for Out-of-Distribution Detection

2024-05-14 · Claus Hofmann, Simon Schmid, Bernhard Lehner, Daniel Klotz 외

Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improv…

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

Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learning

2024-05-15 · Takuo Matsubara

Gradient boosting is a sequential ensemble method that fits a new weaker learner to pseudo residuals at each iteration. We propose Wasserstein gradient boosting, a novel extension of gradient boosting that fits a new wea…

regressionUncertainty Quantification

SnapBoost: A Heterogeneous Boosting Machine

2020-06-17 · NeurIPS 2020 12 · Thomas Parnell, Andreea Anghel, Malgorzata Lazuka, Nikolas Ioannou 외

Modern gradient boosting software frameworks, such as XGBoost and LightGBM, implement Newton descent in a functional space. At each boosting iteration, their goal is to find the base hypothesis, selected from some base h…

MCBoost: Multiple Classifier Boosting for Perceptual Co-clustering of Images and Visual Features

2008-12-01 · NeurIPS 2008 12 · Tae-Kyun Kim, Roberto Cipolla

We present a new co-clustering problem of images and visual features. The problem involves a set of non-object images in addition to a set of object images and features to be co-clustered. Co-clustering is performed in a…

ClusteringObjectobject-detectionObject Detection

Ensembling Sparse Autoencoders

2025-05-21 · Soham Gadgil, Chris Lin, Su-In Lee

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently be…

DiversityLanguage ModelingLanguage Modelling