Background Data Resampling for Outlier-Aware Classification
The problem of learning an image classifier that allows detection of out-of-distribution (OOD) examples, with the help of auxiliary background datasets, is studied. While training with background has been shown to improve OOD detection performance, the optimal choice of such dataset remains an open question, and challenges of data imbalance and computational complexity make it a potentially inefficient or even impractical solution. Targeted at balancing between efficiency and detection quality, a dataset resampling approach is proposed for obtaining a compact yet representative set of background data points. The resampling algorithm takes inspiration from prior work on hard negative mining, performing an iterative adversarial weighting on the background examples and using the learned weights to obtain the subset of desired size. Experiments on different datasets, model architectures and training strategies validate the universal effectiveness and efficiency of adversarially resampled background data. Code is available at https://github.com/JerryYLi/ bg-resample-ood.
Code (1)
Tasks
ClassificationGeneral ClassificationOpen-Ended Question AnsweringOut of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
Support Vector Machine Classifier with Rescaled Huberized Pinball Loss
Support vector machines are widely used in machine learning classification tasks, but traditional SVM models suffer from sensitivity to outliers and instability in resampling, which limits their performance in practical …
Image ClassificationART: Adaptive Resampling-based Training for Imbalanced Classification
Traditional resampling methods for handling class imbalance typically uses fixed distributions, undersampling the majority or oversampling the minority. These static strategies ignore changes in class-wise learning diffi…
Multi-class ClassificationGaining Outlier Resistance with Progressive Quantiles: Fast Algorithms and Theoretical Studies
Outliers widely occur in big-data applications and may severely affect statistical estimation and inference. In this paper, a framework of outlier-resistant estimation is introduced to robustify an arbitrarily given loss…
SADER: Structure-Aware Diffusion Framework with DEterministic Resampling for Multi-Temporal Remote Sensing Cloud Removal
Cloud contamination severely degrades the usability of remote sensing imagery and poses a fundamental challenge for downstream Earth observation tasks. Recently, diffusion-based models have emerged as a dominant paradigm…
Cloud RemovalGranular Ball Twin Support Vector Machine
On Efficient and Scalable Computation of the Nonparametric Maximum Likelihood Estimator in Mixture ModelsTwin support vector machine (TSVM) is an emerging machine learning model with versatile applicability in classifica…
Computational Efficiency